© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14211
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to biology and virology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.59
    Autoritní
    -1.45
     unſ
    -1.41
     purpoſe
    -1.39
     itſelf
    -1.39
     ſtate
    -1.38
     faſt
    -1.38
     pleaſure
    -1.37
     ſever
    -1.36
     $_"
    -1.35
    POSITIVE LOGITS
     
    1.09
    '
    0.91
    ,
    0.85
     in
    0.82
    .
    0.79
    <h2>
    0.75
     is
    0.75
    ↵↵
    0.75
     I
    0.74
    ?
    0.74
    Activations Density 10.267%

    No Known Activations