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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1740
    Prev
    Next
    INDEX
    Explanations

    syntax elements and code structures in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.35
    ↵↵
    -0.34
    SuspendLayout
    -0.32
    teira
    -0.32
     जा
    -0.32
     binding
    -0.31
    Binding
    -0.30
     ponerse
    -0.30
    вере
    -0.29
     Tanya
    -0.29
    POSITIVE LOGITS
     препратки
    0.74
    astify
    0.73
    IsContent
    0.70
     تضيفلها
    0.69
     }{@
    0.68
     typelib
    0.63
    numerusform
    0.57
    JspWriter
    0.56
    UrlResolution
    0.54
    ">//
    0.54
    Activations Density 0.033%

    No Known Activations