© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4204
    Prev
    Next
    INDEX
    Explanations

    terminology related to vehicles and their towing mechanisms

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

    Follows punctuation or determiner tokens

    np_acts-logits-general · gemini-2.0-flash

    winch, chain, anchor, ropes, handle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.57
     invokingState
    -0.54
    nonatomic
    -0.50
     Sze
    -0.49
    ladi
    -0.49
    Enllaces
    -0.48
     excused
    -0.47
     словарь
    -0.46
     dokun
    -0.46
    glement
    -0.45
    POSITIVE LOGITS
     winch
    0.73
     chain
    0.68
     shackles
    0.68
     chains
    0.67
     recovery
    0.67
     win
    0.64
     snatch
    0.64
     anchor
    0.62
    recovery
    0.60
    Recovery
    0.60
    Activations Density 0.219%

    No Known Activations