© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 6792
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between various components and elements

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

    determiners, prepositions, and conjunctions

    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
     EconPapers
    -0.80
     ſind
    -0.80
     kasarigan
    -0.78
    RTLR
    -0.78
     queſta
    -0.77
     deſt
    -0.77
     myſelf
    -0.76
     faſt
    -0.75
     ſta
    -0.74
     createSprite
    -0.73
    POSITIVE LOGITS
    </b>
    0.43
    </th>
    0.41
     thereto
    0.36
    </h4>
    0.35
     thereof
    0.33
     therefor
    0.32
     }).
    0.31
     Ambiental
    0.30
     Dafür
    0.30
     }</
    0.30
    Activations Density 0.823%

    No Known Activations