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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3063
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs and data structures

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

    technical terms and identifiers in code, configuration files, and debug logs.

    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
    endphp
    -0.73
     beginnetje
    -0.67
     صوتيه
    -0.65
     noqa
    -0.64
     يتيمه
    -0.63
    󠁿
    -0.63
     الحره
    -0.62
    UnusedPrivate
    -0.59
    }-*/;
    -0.58
    uxxxx
    -0.58
    POSITIVE LOGITS
    oredCriteria
    0.46
    tvguidetime
    0.43
     nonUne
    0.43
    которые
    0.41
    tothe
    0.38
    Identyfik
    0.36
    kenstock
    0.35
     ویکی‌پدی
    0.35
    withstanding
    0.35
    blurRadius
    0.35
    Activations Density 1.901%

    No Known Activations