© 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. 10641
    Prev
    Next
    INDEX
    Explanations

    technical code snippets and programming-related terms

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

    numeric sequences and digit patterns, particularly multi-digit numbers and numerical codes.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
    MigrationBuilder
    -0.61
    mybatisplus
    -0.40
    上下
    -0.39
     resourceCulture
    -0.38
    WebpackPlugin
    -0.37
    Przypisy
    -0.36
    AutoField
    -0.35
    rzost
    -0.35
    IsMutable
    -0.35
    slidesPer
    -0.35
    POSITIVE LOGITS
    tanleria
    0.56
     ffilmiau
    0.44
     dezelve
    0.43
     LEYENDO
    0.43
    Datuak
    0.42
    etine
    0.41
    reactstrap
    0.40
    RenderAtEndOf
    0.40
    penup
    0.40
    EDEFAULT
    0.40
    Activations Density 0.918%

    No Known Activations