© 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. 1405
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of contradiction

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

    localizing nationalities or origins

    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
    TagMode
    -0.60
     ujednoznacz
    -0.54
     autorytatywna
    -0.51
    tagHelperRunner
    -0.48
    хівовано
    -0.47
     MediatR
    -0.46
    +#+#
    -0.46
     ModelExpression
    -0.45
     licha
    -0.39
    usercontent
    -0.39
    POSITIVE LOGITS
    Canadian
    0.44
    formik
    0.43
     المعيارى
    0.41
    Kdo
    0.41
     Texan
    0.41
     bước
    0.40
    coy
    0.40
    Pick
    0.40
     Toast
    0.40
    Kolor
    0.40
    Activations Density 0.098%

    No Known Activations