© 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 EvalsExportsinterp-engineNEWAPI 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. 2816
    Prev
    Next
    INDEX
    Explanations

    terms associated with force and physical concepts

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

    ending in "ance", "ence", "ace"

    np_acts-logits-general · gemini-2.0-flash

    words ending in -ance or -ence

    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
     Púb
    -0.48
    IfNot
    -0.43
     prière
    -0.42
     Nacionales
    -0.42
     Empres
    -0.42
    <h1>
    -0.42
     Jurí
    -0.42
     pauv
    -0.40
     Escolar
    -0.40
     Ráp
    -0.40
    POSITIVE LOGITS
    ence
    0.93
    ace
    0.91
    itance
    0.88
    ANCE
    0.87
    rance
    0.85
    ance
    0.84
    unce
    0.84
    tice
    0.83
    ances
    0.83
    mace
    0.83
    Activations Density 0.504%

    No Known Activations