© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 84522
    Prev
    Next
    INDEX
    Explanations

    elements related to measurements and quantities in a context, such as the amount of ingredients or items, and actions associated with them

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

    extra or spare quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]=>
    -0.44
     Administrativna
    -0.38
     EClass
    -0.36
    editForm
    -0.33
    getUid
    -0.32
    #+#
    -0.31
    RTHOOK
    -0.31
    tonode
    -0.30
     CF
    -0.29
    Oneof
    -0.29
    POSITIVE LOGITS
     extra
    2.23
     spare
    2.11
    extra
    1.95
    spare
    1.91
     Extra
    1.88
    Extra
    1.87
     EXTRA
    1.71
    Spare
    1.68
     ekstra
    1.67
     Spare
    1.66
    Activations Density 0.086%

    No Known Activations