© 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. 40-GEMMASCOPE-RES-16K
    11. 6735
    Prev
    Next
    INDEX
    Explanations

    content related to experiences and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hereof
    -0.37
     Evidently
    -0.36
     avrebbero
    -0.36
     thereof
    -0.35
    )‏
    -0.34
    捎
    -0.33
    magitan
    -0.33
     jelasnya
    -0.33
     simak
    -0.33
    unduh
    -0.33
    POSITIVE LOGITS
     confirm
    0.66
     dun
    0.58
     Confirm
    0.58
    帖最后由
    0.57
     oso
    0.57
     dunno
    0.56
     lor
    0.54
     Liao
    0.54
     Cannot
    0.54
     nia
    0.54
    Activations Density 0.266%

    No Known Activations