© 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. 10692
    Prev
    Next
    INDEX
    Explanations

    HTML-related structured data and elements

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

    Text following bracketed HTML or XML tags

    np_acts-logits-general · gemini-2.0-flash

    Immun, Japanese pronouns, Group, Chemistry, Method, Substance, Host

    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
     extranjero
    -0.34
     pitä
    -0.34
     indeed
    -0.33
     encabez
    -0.32
    ßerdem
    -0.31
    zczegól
    -0.31
    AsUp
    -0.31
     invitamos
    -0.30
     ilç
    -0.30
    ském
    -0.30
    POSITIVE LOGITS
    __(/*!
    1.08
    Hentet
    0.73
     the
    0.69
    extAlignment
    0.65
    endphp
    0.65
    }{*}{
    0.64
     esternos
    0.62
     a
    0.61
    Portale
    0.61
    ValueStyle
    0.60
    Activations Density 0.321%

    No Known Activations