© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 107346
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters associated with data processing or programming in a specific language

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

    ngx and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perlindungan
    -0.48
     –
    -0.47
     a
    -0.47
     an
    -0.43
     —
    -0.43
     penghar
    -0.42
     wszyst
    -0.42
     verdaderamente
    -0.42
    {~
    -0.42
     vähän
    -0.42
    POSITIVE LOGITS
    bootstrapcdn
    1.04
     betweenstory
    0.89
    Personendaten
    0.80
     NSCoder
    0.75
    fjspx
    0.74
     سكانية
    0.73
    ViewImports
    0.73
     contextLoads
    0.73
    tagHelperRunner
    0.71
     GoogleFonts
    0.71
    Activations Density 0.349%

    No Known Activations