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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16224
    Prev
    Next
    INDEX
    Explanations

    references to stakeholders involved in public health emergencies and policy-making

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

    Often follows conjunctions and commas

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
     Làm
    -0.31
     short
    -0.31
     corrected
    -0.30
     człowie
    -0.30
     beträgt
    -0.30
    UnifiedTopology
    -0.30
     Abschied
    -0.30
     Short
    -0.30
    Làm
    -0.30
    短
    -0.29
    POSITIVE LOGITS
     politicians
    1.03
     universities
    0.99
     sociologists
    0.98
     policymakers
    0.97
     insurers
    0.96
     retailers
    0.91
     legislators
    0.91
     academia
    0.90
     psychiatrists
    0.90
     governments
    0.90
    Activations Density 0.371%

    No Known Activations