© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 42142
    Prev
    Next
    INDEX
    Explanations

    references to contributors in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     estekak
    -1.96
    GEBURTSDATUM
    -1.26
    oredCriteria
    -1.17
     виправивши
    -1.13
     kasarigan
    -1.11
    verwijspagina
    -1.02
    parsedMessage
    -1.02
     ContentValues
    -1.02
    expandindo
    -1.01
    createCanvas
    -0.95
    POSITIVE LOGITS
    OGND
    2.05
    JoinTable
    1.51
    HasAnnotation
    1.37
    Хро
    1.18
     CONTRIBUTORS
    1.05
    LLocation
    0.39
    -
    0.36
    ,
    0.36
     deal
    0.35
    lar
    0.34
    Activations Density 0.000%

    No Known Activations