© 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
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12791
    Prev
    Next
    INDEX
    Explanations

    connections between local government actions and community outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.84
    httphttps
    -0.72
    webElementXpaths
    -0.72
    ɵɵ
    -0.67
    ViewImports
    -0.65
     CanadaChoose
    -0.64
    migrationBuilder
    -0.63
    脚注の使い方
    -0.62
     esternos
    -0.62
     ब्रेकडाउन
    -0.61
    POSITIVE LOGITS
     ändå
    0.39
    光是
    0.35
     things
    0.35
    Сим
    0.35
     işte
    0.34
     Schi
    0.34
     manage
    0.34
     offenen
    0.33
    entir
    0.33
     Zuge
    0.32
    Activations Density 0.976%

    No Known Activations