© 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. 20-GEMMASCOPE-RES-16K
    6. 14637
    Prev
    Next
    INDEX
    Explanations

    instances of the word "visit" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abstrato
    -0.63
    IntoConstraints
    -0.59
     CURIAM
    -0.56
     myſelf
    -0.55
    alegal
    -0.55
     spéciaux
    -0.54
     avulla
    -0.54
     configurer
    -0.54
     poffible
    -0.54
     juridiques
    -0.52
    POSITIVE LOGITS
     visit
    1.23
    visit
    1.14
     Visit
    1.12
     VISIT
    1.10
     visits
    1.09
    VISIT
    1.02
     Visits
    1.00
    visits
    0.96
    Visit
    0.96
     visited
    0.94
    Activations Density 0.037%

    No Known Activations