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. 11-GEMMASCOPE-RES-16K
    6. 5791
    Prev
    Next
    INDEX
    Explanations

    instances of the word "visit" and its variations suggesting physical visits or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
     
    -0.73
    <th>
    -0.73
     P
    -0.69
     money
    -0.69
     K
    -0.68
    </b>
    -0.67
    -
    -0.63
     C
    -0.62
     he
    -0.62
    ,
    -0.61
    POSITIVE LOGITS
     VISIT
    1.93
     Visits
    1.75
    VISIT
    1.70
     visit
    1.66
     visits
    1.65
     Visit
    1.60
    visit
    1.55
    visits
    1.54
    Visit
    1.53
     Visiting
    1.51
    Activations Density 0.045%

    No Known Activations