© 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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1442
    Prev
    Next
    INDEX
    Explanations

    scientific terms and phrases related to biological processes and research methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Latin phrases/words

    np_acts-logits-general · gemini-2.0-flash

    in vivo, in vitro, per se

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.35
    ScopeManager
    -0.33
     times
    -0.32
    횟
    -0.31
     couvercle
    -0.29
    parsedMessage
    -0.29
    BeginContext
    -0.29
     allan
    -0.28
     casque
    -0.28
    EndContext
    -0.28
    POSITIVE LOGITS
    tvguidetime
    0.71
    хьтан
    0.68
     Walkover
    0.67
    цездатний
    0.60
    msgTypes
    0.57
    libft
    0.56
    ⎩
    0.56
    Kjelder
    0.52
    RUnlock
    0.52
    rawDesc
    0.52
    Activations Density 0.223%

    No Known Activations