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

    Neuronpedia

    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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13447
    Prev
    Next
    INDEX
    Explanations

    parts of a narrative that involve character interactions and emotional expressions

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

    Characters after a number

    np_acts-logits-general · gemini-2.0-flash

    technical terms and foreign words

    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
    LookAnd
    -0.52
    AndEndTag
    -0.35
    Referencer
    -0.34
    Golf
    -0.33
    周泽楷
    -0.33
    叶凌天
    -0.33
    南浔
    -0.33
    fgets
    -0.33
     étoit
    -0.32
    óngase
    -0.32
    POSITIVE LOGITS
     betweenstory
    0.84
     ब्रेकडाउन
    0.65
    EndContext
    0.63
    UserScript
    0.62
    Vidite
    0.59
    jsii
    0.57
    XtraReports
    0.55
     CanadaChoose
    0.55
    migrationBuilder
    0.53
    WebElementEntity
    0.53
    Activations Density 0.165%

    No Known Activations