© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11143
    Prev
    Next
    INDEX
    Explanations

    inquiries about trends and variations in data

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

    Followed by a non-alphanumeric token

    np_acts-logits-general · gemini-2.0-flash

    history book

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    cient
    -0.40
    litt
    -0.39
     pui
    -0.39
     erk
    -0.38
    chos
    -0.38
    gew
    -0.37
    yl
    -0.36
    jo
    -0.36
     السب
    -0.36
     cry
    -0.35
    POSITIVE LOGITS
     estekak
    0.56
    thâu
    0.55
    aronder
    0.54
     ويكيميديا
    0.48
    IntoConstraints
    0.48
     betweenstory
    0.48
    recated
    0.46
    了嗎
    0.45
     saites
    0.43
    jsxFileName
    0.43
    Activations Density 1.046%

    No Known Activations