© 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. 35-GEMMASCOPE-RES-16K
    11. 13957
    Prev
    Next
    INDEX
    Explanations

    terms related to academic or scientific disciplines

    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
     enfermo
    -0.23
     varandra
    -0.23
     psicológica
    -0.23
     fundus
    -0.22
     games
    -0.22
    MERCE
    -0.22
     OTHERWISE
    -0.21
    ์
    -0.21
     separado
    -0.21
    مقاله
    -0.21
    POSITIVE LOGITS
    ors
    0.99
    ory
    0.87
    ORS
    0.84
    orship
    0.82
    ured
    0.78
     HasFactory
    0.76
    ori
    0.73
    orem
    0.73
    uring
    0.72
    findpost
    0.72
    Activations Density 0.386%

    No Known Activations