© 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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4537
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographic locations or administrative divisions

    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
     AssemblyCulture
    -0.90
    MigrationBuilder
    -0.82
    ंदीखरीदारी
    -0.80
    IntoConstraints
    -0.80
    antMatchers
    -0.79
     cherchés
    -0.78
    脚注の使い方
    -0.73
    contentLoaded
    -0.72
    ########.
    -0.71
    abestanden
    -0.70
    POSITIVE LOGITS
    my
    0.54
     my
    0.53
    phone
    0.48
    vare
    0.47
    tyn
    0.47
    ztály
    0.46
    kit
    0.45
    Identifier
    0.45
     chính
    0.44
    例文帳に追加
    0.43
    Activations Density 1.928%

    No Known Activations