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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6745
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and highway contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Walk
    -0.66
    Walking
    -0.63
     WALK
    -0.63
    aarrggbb
    -0.63
     Walk
    -0.63
     Walking
    -0.63
     walked
    -0.61
     walks
    -0.61
    WALK
    -0.60
     actionMode
    -0.60
    POSITIVE LOGITS
     freeway
    1.11
     motorway
    1.05
     highway
    1.01
     interstate
    0.97
     Interstate
    0.95
     Expressway
    0.92
     Freeway
    0.92
     toll
    0.92
     Highway
    0.91
     exit
    0.91
    Activations Density 0.144%

    No Known Activations