© 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. 19-GEMMASCOPE-RES-16K
    11. 11823
    Prev
    Next
    INDEX
    Explanations

    references to medical research and support

    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
    WithFormat
    -0.77
    ::::::::
    -0.74
     ]];
    -0.72
    ment
    -0.72
     '{@
    -0.71
    *)&
    -0.69
    antMatchers
    -0.68
     }}">
    -0.68
     ذات
    -0.67
    endphp
    -0.66
    POSITIVE LOGITS
    1
    1.09
    st
    0.89
    ⁄
    0.69
    0
    0.68
     anis
    0.65
    2
    0.63
     Achille
    0.63
     dieß
    0.60
     Eleventh
    0.60
    DAOImpl
    0.60
    Activations Density 0.630%

    No Known Activations