Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53729
    Prev
    Next
    INDEX
    Explanations

    programming-related function definitions and keywords

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

    Anonymous function declarations used in defer statements for tracing/instrumentation in Go code, typically containing logic to capture status codes and end tracing spans.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.35
    package
    -0.35
    IContainer
    -0.34
    ßig
    -0.32
    Distinct
    -0.32
     զ
    -0.32
    Lu
    -0.31
    <strong>
    -0.31
    Этот
    -0.31
     Entdecken
    -0.30
    POSITIVE LOGITS
    abestanden
    0.71
     utafitiHapana
    0.69
     незавершена
    0.66
    gameserver
    0.66
    Tikang
    0.63
    UnusedPrivate
    0.62
    Personendaten
    0.62
     queſta
    0.59
    сылкі
    0.58
     Biôgrafia
    0.57
    Activations Density 0.133%

    No Known Activations