© 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. 24-GEMMASCOPE-RES-16K
    11. 3505
    Prev
    Next
    INDEX
    Explanations

    numerical data and specifications related to sampling and parameters

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

    Values or steps within a defined range

    np_acts-logits-general · gemini-2.0-flash

    every `[time/quantity]`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.47
    temporada
    -0.43
     peringkat
    -0.35
    twimg
    -0.35
     Magno
    -0.34
    譜
    -0.34
     regionales
    -0.33
     khỏi
    -0.33
    鋼
    -0.32
     sezonu
    -0.32
    POSITIVE LOGITS
     spaced
    0.81
     spacing
    0.73
    spaced
    0.68
     Spacing
    0.67
     periodic
    0.64
     interval
    0.63
     intervals
    0.62
    间隔
    0.62
     Intervals
    0.59
     periodically
    0.59
    Activations Density 0.515%

    No Known Activations