© 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. 110383
    Prev
    Next
    INDEX
    Explanations

    references to funding and support related to projects or events

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

    grants, funding, and sponsors

    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
     متعلقه
    -0.41
    Carriera
    -0.38
     either
    -0.35
     noDo
    -0.33
    Either
    -0.33
     WebDriverWait
    -0.32
     notoriously
    -0.32
     CHtml
    -0.32
    ostom
    -0.32
     makeshift
    -0.32
    POSITIVE LOGITS
     support
    1.02
     supported
    1.00
     sponsors
    0.97
     funding
    0.95
    supported
    0.93
     Supported
    0.93
     sponsoring
    0.89
     sponsor
    0.85
    Supported
    0.85
    support
    0.84
    Activations Density 0.021%

    No Known Activations