© 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. 101509
    Prev
    Next
    INDEX
    Explanations

    references to specific biological processes or medical conditions

    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
    RenderAtEndOf
    -0.66
    ImageContext
    -0.53
    WindowConstants
    -0.53
    RectangleBorder
    -0.52
    ynomial
    -0.51
     defaultstate
    -0.51
    LLocation
    -0.50
    xase
    -0.49
    MLLoader
    -0.49
     StringTokenizer
    -0.48
    POSITIVE LOGITS
     Audiodateien
    0.44
    まさか
    0.37
    GEBURTSDATUM
    0.34
     plausible
    0.32
    Ответить
    0.29
    NameInMap
    0.29
    IUrlHelper
    0.29
     possible
    0.29
     vero
    0.29
    SetBool
    0.29
    Activations Density 0.226%

    No Known Activations