© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1943
    Prev
    Next
    INDEX
    Explanations

    coding syntax and elements related to web development or programming instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming language syntax and code structure elements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    code in statically-typed programming languages, particularly Swift and similar languages with explicit type annotations and member access patterns.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    source code snippets, particularly Swift/Protobuf-style accessor and field-handling patterns with underscores, typed variables, and heavy punctuation like parentheses and braces.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lieben
    -0.32
    ंदीखरीदारी
    -0.31
    せ
    -0.30
    udra
    -0.30
    stateProvider
    -0.29
    gridy
    -0.28
    retudo
    -0.27
     corner
    -0.26
    decomposition
    -0.25
    autoload
    -0.25
    POSITIVE LOGITS
    OGND
    0.72
    :+:
    0.62
     Dart
    0.59
     ویکی‌پدی
    0.57
    +#+
    0.57
    Tikang
    0.54
     kaynağından
    0.53
     Biôgrafia
    0.53
    Dart
    0.50
    hmigung
    0.50
    Activations Density 0.306%

    No Known Activations