© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 80345
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to geographic locations and their characteristics

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

    populated places in Russia

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Sementara
    -0.42
    脚注の使い方
    -0.39
     venezolano
    -0.36
    havn
    -0.36
     Kasih
    -0.36
     Verpackung
    -0.34
     Thessaloniki
    -0.34
    Спољашње
    -0.34
     Venedig
    -0.34
     propias
    -0.33
    POSITIVE LOGITS
    MigrationBuilder
    0.57
    ChromeDriver
    0.55
    oneofs
    0.52
     ChromeDriver
    0.51
    IsMutable
    0.48
    tangentMode
    0.46
    CppMethod
    0.46
    styleType
    0.46
    jspb
    0.45
     Administrativna
    0.45
    Activations Density 0.024%

    No Known Activations