© 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
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 6767
    Prev
    Next
    INDEX
    Explanations

    elements related to constraints and parameters in data structures or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.58
    TagMode
    -0.56
     виправивши
    -0.53
    tanleria
    -0.51
    ніципалі
    -0.50
    ch
    -0.45
    pernicus
    -0.44
    ches
    -0.42
    RenderAtEndOf
    -0.42
    Personendaten
    -0.41
    POSITIVE LOGITS
     Char
    3.16
     char
    3.13
    Char
    2.94
     CHAR
    2.78
    char
    2.59
    CHAR
    2.31
     charter
    2.30
     Charter
    2.28
     Charlie
    2.22
     Chart
    2.08
    Activations Density 0.365%

    No Known Activations