© 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. 20-GEMMASCOPE-RES-16K
    11. 14294
    Prev
    Next
    INDEX
    Explanations

    references to enrollment processes and medical or experimental settings

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

    "well" followed by a preposition/punctuation

    np_acts-logits-general · gemini-2.0-flash

    treatment and relief

    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
     akad
    -0.37
     houſe
    -0.32
     popr
    -0.32
     leaſt
    -0.32
     tours
    -0.32
     Jefus
    -0.32
    fär
    -0.32
     poffe
    -0.32
     RIPRODUZIONE
    -0.31
    註
    -0.31
    POSITIVE LOGITS
    DockStyle
    0.65
    ніципалі
    0.60
    Demografie
    0.54
     HttpNotFound
    0.54
     ویکی‌پدی
    0.53
    mentaux
    0.53
    PerformLayout
    0.52
    InitVars
    0.50
    ondissement
    0.49
    DoubleQuotes
    0.49
    Activations Density 2.696%

    No Known Activations