© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 12133
    Prev
    Next
    INDEX
    Explanations

    words related to the genus of plants or animals called "Cress" or similar sounding terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    انتهای
    -0.48
    sidemargin
    -0.48
     jsonify
    -0.44
     objectMapper
    -0.43
    Geografi
    -0.42
    endpush
    -0.40
    bootstrapcdn
    -0.40
    PostBack
    -0.40
    レンタイン
    -0.39
     Plum
    -0.39
    POSITIVE LOGITS
     cre
    0.91
     Cre
    0.87
    Cre
    0.86
    cre
    0.78
     CRE
    0.73
    CRE
    0.63
    crew
    0.55
     Crew
    0.53
     cré
    0.52
     Crews
    0.52
    Activations Density 0.081%

    No Known Activations