© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 73434
    Prev
    Next
    INDEX
    Explanations

    common phrases, words, or patterns of speech that convey a sense of gratitude or excitement

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

    end punctuation

    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
     SwitchCompat
    -0.69
    曖昧さ回避
    -0.64
    ArrowToggle
    -0.64
    AISSEE
    -0.60
    省市镇
    -0.55
    OOTDTY
    -0.55
     الرياضيه
    -0.54
    лтемелер
    -0.54
     Himo
    -0.53
    Abit
    -0.53
    POSITIVE LOGITS
    elif
    0.35
     Brito
    0.33
     Kelley
    0.30
    Sincerely
    0.30
    <h1>
    0.30
     тем
    0.29
    Sinopsis
    0.29
    package
    0.29
    """
    0.28
    """
    0.28
    Activations Density 0.164%

    No Known Activations