© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 95589
    Prev
    Next
    INDEX
    Explanations

    references to numbers and numerical concepts

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

    numeral reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Déf
    -0.41
     Trabalho
    -0.40
     Vogt
    -0.40
    ILayout
    -0.40
     Desenvolvimento
    -0.39
     with
    -0.39
    ्
    -0.39
    ọt
    -0.38
     fosters
    -0.38
     and
    -0.37
    POSITIVE LOGITS
     numero
    1.73
     Numero
    1.64
    Numero
    1.55
    numero
    1.53
     número
    1.27
     number
    1.20
     Number
    1.17
     NUMBER
    1.13
    Number
    1.12
     numéro
    1.10
    Activations Density 0.001%

    No Known Activations