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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 23224
    Prev
    Next
    INDEX
    Explanations

    references to dividers and binders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.57
    tableFuture
    -0.50
    getTime
    -0.49
     
    -0.49
     Spisak
    -0.49
    mployment
    -0.49
     expédi
    -0.48
     autorytatywna
    -0.47
    =()
    -0.47
     São
    -0.47
    POSITIVE LOGITS
    Divider
    0.95
    divider
    0.94
     Divider
    0.92
     divider
    0.82
    Binder
    0.82
     binder
    0.76
     Binder
    0.75
    binder
    0.73
     Liner
    0.57
    liner
    0.56
    Activations Density 0.003%

    No Known Activations