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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 975
    Prev
    Next
    INDEX
    Explanations

    references to guidance and guidelines related to emergency preparedness and response protocols

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

    guidance and guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     cast
    -0.28
     réguli
    -0.27
    EndContext
    -0.27
    /**
    -0.25
    AutoField
    -0.25
    WriteLiteral
    -0.25
     bet
    -0.24
    machte
    -0.24
     férias
    -0.24
     cut
    -0.24
    POSITIVE LOGITS
     guidance
    0.90
     guidelines
    0.84
    Guidance
    0.83
     Guidance
    0.83
    guidance
    0.82
     guideline
    0.79
    guidelines
    0.79
    Guidelines
    0.78
     Guidelines
    0.77
     recommendations
    0.77
    Activations Density 0.044%

    No Known Activations