© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 107544
    Prev
    Next
    INDEX
    Explanations

    information related to website design and maintenance

    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
    BagConstraints
    -0.37
     BitSet
    -0.35
     ángeles
    -0.35
     yyr
    -0.35
    unknownFields
    -0.33
    getRequest
    -0.33
     سو
    -0.32
     tor
    -0.32
     monasterio
    -0.31
    InsertCommand
    -0.31
    POSITIVE LOGITS
    Clik
    0.59
    verwijspagina
    0.58
    ésultats
    0.53
     biographies
    0.52
    rungsseite
    0.50
    ſelves
    0.49
    WebControls
    0.49
     EconPapers
    0.48
    Tembelea
    0.48
    iſen
    0.47
    Activations Density 0.021%

    No Known Activations