© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 5657
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, organizations, or entities involved in events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     always
    -0.88
     hasn
    -0.83
     never
    -0.81
     isn
    -0.77
     תמיד
    -0.76
     siempre
    -0.75
    always
    -0.75
     lately
    -0.75
     nunca
    -0.74
     wcześniej
    -0.74
    POSITIVE LOGITS
     embarked
    0.66
     began
    0.65
     became
    0.58
     suddenly
    0.58
     underwent
    0.56
     officially
    0.55
     formally
    0.55
     unexpectedly
    0.55
     abruptly
    0.54
     joined
    0.53
    Activations Density 0.775%

    No Known Activations