© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 11794
    Prev
    Next
    INDEX
    Explanations

    programming constructs and their respective parameters related to data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.66
     BoxDecoration
    -0.65
    principalTable
    -0.52
    simpleType
    -0.51
    Ответить
    -0.49
    romolecules
    -0.47
    onOptions
    -0.47
     insuffisamment
    -0.46
     trekken
    -0.45
     gæ
    -0.45
    POSITIVE LOGITS
     index
    1.16
     position
    1.02
    idx
    1.01
     idx
    0.99
     Index
    0.98
    index
    0.98
     offset
    0.97
    Index
    0.95
     indice
    0.94
    offset
    0.93
    Activations Density 1.164%

    No Known Activations