© 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. 13631
    Prev
    Next
    INDEX
    Explanations

    nouns related to roles, positions, or responsibilities in various contexts

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

    followed by "of", "with", or "to"

    np_acts-logits-general · gemini-2.0-flash

    relationships and interactions

    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
    makeConstraints
    -0.56
    aziland
    -0.51
     kaarangay
    -0.50
    LOAT
    -0.49
    .*")]
    -0.49
    yer
    -0.48
    SharedCtor
    -0.48
     nakalista
    -0.48
    migrationBuilder
    -0.47
     Turtle
    -0.47
    POSITIVE LOGITS
    AddTagHelper
    0.51
    withIdentifier
    0.45
    addComponent
    0.35
    Välislingid
    0.35
     createSprite
    0.31
    ConstraintMaker
    0.30
    óngase
    0.30
    ientôt
    0.30
    ="@+
    0.29
    égorie
    0.28
    Activations Density 1.304%

    No Known Activations