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. 15739
    Prev
    Next
    INDEX
    Explanations

    words that evaluate health impacts as positive or negative

    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
     الحره
    -0.64
    featureID
    -0.60
    JspWriter
    -0.59
    anglès
    -0.59
    daging
    -0.59
    atigable
    -0.58
    Datuak
    -0.58
     Hackett
    -0.57
    setVerticalGroup
    -0.57
    StoryboardSegue
    -0.54
    POSITIVE LOGITS
     beneficial
    1.18
     detrimental
    0.93
     Beneficial
    0.93
     harmful
    0.87
     benefit
    0.81
     healthy
    0.76
    benef
    0.76
     damaging
    0.70
     boon
    0.69
     benefiting
    0.68
    Activations Density 0.187%

    No Known Activations