© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 19774
    Prev
    Next
    INDEX
    Explanations

    names or terms associated with "bra" materials and related concepts

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

    Bradshaw, Brachytherapy, Brazil, Brady, BRABUS

    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
    Hochspringen
    -0.31
    plain
    -0.30
    Plain
    -0.29
     seca
    -0.29
     plain
    -0.28
    Obr
    -0.28
     Plain
    -0.27
     pemuda
    -0.27
     Objek
    -0.27
    гом
    -0.27
    POSITIVE LOGITS
    SequentialGroup
    0.79
    Bra
    0.77
     Bra
    0.73
    yntaxException
    0.69
     IBOutlet
    0.69
     estekak
    0.67
     BRA
    0.65
    bra
    0.61
     bra
    0.60
    Geplaatst
    0.60
    Activations Density 0.039%

    No Known Activations