© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 12864
    Prev
    Next
    INDEX
    Explanations

    expressions of disbelief or confusion, often punctuated by exclamatory language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.96
    CrossRef
    -0.77
    +:+
    -0.63
    __":
    
    -0.61
     CURIAM
    -0.61
     inoxydable
    -0.59
    arakhand
    -0.57
    abello
    -0.55
    >--}}
    -0.53
     useParams
    -0.53
    POSITIVE LOGITS
     hell
    0.86
     heck
    0.82
     HELL
    0.62
     fuck
    0.60
     Hell
    0.58
    Diwedd
    0.58
     did
    0.57
    DrawerToggle
    0.56
    queryInterface
    0.55
     freaking
    0.54
    Activations Density 0.125%

    No Known Activations