© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11122
    Prev
    Next
    INDEX
    Explanations

    phrases related to visiting or interactions involving visitors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "visit"

    np_acts-logits-general · gemini-2.0-flash

    act of visiting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    IntoConstraints
    -0.60
     abstrato
    -0.59
    alegal
    -0.57
    klere
    -0.54
     myſelf
    -0.53
     CURIAM
    -0.52
     configurer
    -0.52
    seamnă
    -0.52
     TÉCN
    -0.51
     armées
    -0.51
    POSITIVE LOGITS
     visit
    1.15
    visit
    1.13
     Visit
    1.09
     VISIT
    1.07
     visits
    1.07
    Visit
    1.03
     Visits
    1.01
    VISIT
    0.98
    visits
    0.96
     visitor
    0.93
    Activations Density 0.061%

    No Known Activations