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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6967
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "visit" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aupun
    -0.69
     dotenv
    -0.57
    otide
    -0.56
     celo
    -0.54
     tilgjenge
    -0.52
     שוליים
    -0.52
    xtension
    -0.52
     dàng
    -0.52
     umbre
    -0.51
    <th>
    -0.51
    POSITIVE LOGITS
     Visitors
    0.98
     VISIT
    0.94
     visitors
    0.92
    Visitors
    0.92
     Visits
    0.86
     Visiting
    0.84
    visits
    0.83
    VISIT
    0.83
     visits
    0.82
    ThroughAttribute
    0.81
    Activations Density 0.052%

    No Known Activations