Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8147
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific identifiers, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.69
    CloseOperation
    -0.69
     للاسماء
    -0.60
    bufio
    -0.60
    XtraReports
    -0.59
    yarnpkg
    -0.59
    sizeCache
    -0.59
    tvguidetime
    -0.59
    RUnlock
    -0.59
    NUMX
    -0.58
    POSITIVE LOGITS
     Antiquities
    0.31
    @
    0.30
     слуша
    0.29
     ih
    0.29
     @
    0.27
     CanadaChoose
    0.27
    Segu
    0.27
     ex
    0.27
    **
    0.26
    showError
    0.26
    Activations Density 0.366%

    No Known Activations