© 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. 9-GEMMASCOPE-RES-16K
    11. 10392
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of individuals and organizations

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

    preceding accented characters

    np_acts-logits-general · gemini-2.0-flash

    Alonso-Betanzos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    힣
    -0.49
    دانشنامهٔ
    -0.48
    EndInit
    -0.47
    IntoConstraints
    -0.45
     Deva
    -0.43
    @[+][
    -0.43
    EDEFAULT
    -0.43
     Begegn
    -0.42
     competencia
    -0.42
    راسیون
    -0.42
    POSITIVE LOGITS
    MERCIAL
    0.41
    mybatisplus
    0.41
     betweenstory
    0.40
    BagLayout
    0.39
    ècie
    0.39
    WriteTagHelper
    0.39
    Tembelea
    0.38
    órmula
    0.37
    brenner
    0.37
     Sond
    0.37
    Activations Density 0.949%

    No Known Activations