© 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
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15429
    Prev
    Next
    INDEX
    Explanations

    references to array and data manipulation functions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.79
    RenderAtEndOf
    -0.76
     resourceCulture
    -0.70
     disambiguazione
    -0.68
    transQ
    -0.67
     HasFactory
    -0.66
    featureID
    -0.66
    PerformLayout
    -0.63
     tartalomajánló
    -0.63
    SequentialGroup
    -0.61
    POSITIVE LOGITS
    asarray
    0.64
     numpy
    0.61
    ndarray
    0.57
    numpy
    0.56
     tensor
    0.52
    tensor
    0.52
     ndarray
    0.49
    array
    0.47
     numerical
    0.43
    Tensor
    0.42
    Activations Density 0.091%

    No Known Activations