© 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. 34-GEMMASCOPE-RES-16K
    11. 15355
    Prev
    Next
    INDEX
    Explanations

    key actions or terms related to ongoing processes or repeated evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ante
    -0.34
     Ger
    -0.29
    نج
    -0.28
    removeAttribute
    -0.27
     Gang
    -0.27
     chum
    -0.27
    KindOfClass
    -0.27
    里
    -0.27
    里的
    -0.27
     Ware
    -0.27
    POSITIVE LOGITS
    downs
    1.12
    ups
    1.11
    outs
    1.08
     ups
    1.03
    Ups
    1.00
    offs
    0.99
     outs
    0.96
     downs
    0.96
    Downs
    0.93
     offs
    0.92
    Activations Density 0.373%

    No Known Activations