Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 295
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and scientific investigative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    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
    -0.67
    
    -0.63
    t
    -0.63
    p
    -0.62
    ج
    -0.62
    f
    -0.61
    Slf
    -0.60
    a
    -0.59
    P
    -0.59
    moveToFirst
    -0.59
    POSITIVE LOGITS
     myſelf
    0.98
     themſelves
    0.98
     doubtnut
    0.96
     whoſe
    0.89
     himſelf
    0.87
     itſelf
    0.84
     ―――――
    0.80
     Efq
    0.79
     juſt
    0.78
     fometimes
    0.77
    Activations Density 2.240%

    No Known Activations