© 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. 84829
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns, particularly "I" and "you"

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

    questions and conditional statements

    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
    !*\
    -0.60
    WriteBarrier
    -0.57
    trl
    -0.54
     صوتيه
    -0.50
    RenderAtEndOf
    -0.49
    bootstrapcdn
    -0.48
    KL
    -0.47
     Nil
    -0.47
     maat
    -0.46
    ことにしました
    -0.46
    POSITIVE LOGITS
    Apakah
    0.65
     Apakah
    0.62
     whether
    0.58
    rungsseite
    0.58
    Czy
    0.55
    是否
    0.54
     apakah
    0.54
     האם
    0.53
    whether
    0.52
     WHETHER
    0.52
    Activations Density 0.023%

    No Known Activations