© 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. 19-GEMMASCOPE-RES-16K
    6. 1788
    Prev
    Next
    INDEX
    Explanations

    medical terms and contextual references related to death and severe injury

    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
    kháu
    -0.68
    __(/*!
    -0.58
    TableAdapter
    -0.57
    actionMode
    -0.55
     mergeFrom
    -0.55
     mxArray
    -0.54
    KommentareTeilen
    -0.51
     Initialise
    -0.50
    createComponent
    -0.50
     endwhile
    -0.49
    POSITIVE LOGITS
     rather
    0.66
    водства
    0.58
     occurred
    0.57
    ADVERTISEMENT
    0.56
    이다
    0.55
    DebuggerNonUser
    0.54
    rather
    0.54
    例文帳に追加
    0.53
    랍
    0.53
     явля
    0.53
    Activations Density 0.084%

    No Known Activations