© 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 EvalsExportsAPI 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. 55343
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "is" and related forms, indicating a focus on statement or descriptive contexts

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

    possessive marker or 'is' before noun

    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
    principalTable
    -0.71
    parsedMessage
    -0.61
    BeginContext
    -0.60
     snippetHide
    -0.57
     bezeichneter
    -0.51
     صوتيه
    -0.47
     Roskov
    -0.46
    AutoField
    -0.46
     AspNetCore
    -0.44
     Winaray
    -0.44
    POSITIVE LOGITS
    coste
    0.45
     Schall
    0.43
    hala
    0.43
    sila
    0.42
    laku
    0.42
    ocin
    0.42
    ener
    0.42
     Brasília
    0.42
    笛
    0.42
    atzes
    0.41
    Activations Density 0.020%

    No Known Activations