© 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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13578
    Prev
    Next
    INDEX
    Explanations

    examples and instances related to measurements and parameters in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.45
     contextLoads
    -0.45
    inSlope
    -0.40
    SequentialGroup
    -0.40
     Generales
    -0.39
     doInBackground
    -0.37
     JpaRepository
    -0.35
     Gesang
    -0.34
     endregion
    -0.33
     hendes
    -0.33
    POSITIVE LOGITS
    example
    0.72
     example
    0.70
    Example
    0.66
    EXAMPLE
    0.65
     exempel
    0.61
     esempio
    0.60
     Example
    0.59
     exemplo
    0.57
     voorbeeld
    0.56
     например
    0.56
    Activations Density 0.828%

    No Known Activations