© 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. 39-GEMMASCOPE-RES-16K
    11. 4247
    Prev
    Next
    INDEX
    Explanations

    descriptions of unique features or characteristics of characters or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;-)
    -0.71
    :-)
    -0.67
     …..
    -0.60
     :-(
    -0.57
     ….
    -0.57
     ;-)
    -0.56
     …”
    -0.54
    :-(
    -0.53
    ,–
    -0.49
     :-)
    -0.48
    POSITIVE LOGITS
     aswell
    0.85
     ingame
    0.80
     iirc
    0.80
     lmao
    0.74
     irl
    0.67
    MfG
    0.67
     IIRC
    0.65
     reccomend
    0.65
     ибо
    0.63
    UseVisualStyle
    0.60
    Activations Density 1.207%

    No Known Activations