© 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. 13819
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical data, matching, and federal financial matters

    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
    RenderAtEndOf
    -0.65
    󠁴
    -0.36
    EDEFAULT
    -0.33
     autorytatywna
    -0.33
     समीक्षाओं
    -0.33
     Paglinawan
    -0.32
    outState
    -0.32
     BorderLayout
    -0.31
     surla
    -0.30
     通販
    -0.30
    POSITIVE LOGITS
     match
    3.83
     matching
    3.36
    match
    3.34
     Match
    3.30
     matches
    3.25
     MATCH
    3.25
     matched
    3.17
    Match
    3.17
     Matching
    3.11
    MATCH
    2.95
    Activations Density 0.944%

    No Known Activations