© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19672
    Prev
    Next
    INDEX
    Explanations

    terms related to specification and referencing within textual contexts

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

    referenced specific items

    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-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
     поми
    -0.35
    ALSO
    -0.35
    ändler
    -0.33
    åter
    -0.32
    itulo
    -0.31
    又有
    -0.31
    tulo
    -0.30
    Et
    -0.30
    FDRE
    -0.29
    Physician
    -0.29
    POSITIVE LOGITS
    nezeu
    0.61
     متعلقه
    0.57
    setupUi
    0.55
    UnusedPrivate
    0.53
    bootstrapcdn
    0.53
    resaid
    0.52
     useAppContext
    0.52
    ỡng
    0.52
     desired
    0.52
    RegressionTest
    0.52
    Activations Density 0.072%

    No Known Activations