© 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. 16234
    Prev
    Next
    INDEX
    Explanations

    instances of resignation and political controversy

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

    preceding verbs indicating actions/attempts

    np_acts-logits-general · gemini-2.0-flash

    actions and outcomes

    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
    hyrchwyd
    -0.33
     umož
    -0.31
    WebVitals
    -0.31
     nikdy
    -0.30
     nabíz
    -0.30
     terjadi
    -0.30
     conscientes
    -0.29
     sensazione
    -0.28
     další
    -0.28
     DbSet
    -0.26
    POSITIVE LOGITS
     ModelExpression
    0.78
     himself
    0.73
    MigrationBuilder
    0.67
    ConstraintMaker
    0.61
    himself
    0.61
     surla
    0.58
     defaultstate
    0.52
     australis
    0.52
    تقاوى
    0.51
    ftagPool
    0.50
    Activations Density 0.698%

    No Known Activations