© 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. 7635
    Prev
    Next
    INDEX
    Explanations

    code structure and elements related to class and method definitions in programming

    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
    hrens
    -0.52
    abetes
    -0.52
    ielli
    -0.50
     tiled
    -0.49
    PostInfinity
    -0.49
    ChildScrollView
    -0.48
     nematodes
    -0.48
    ridis
    -0.47
    alista
    -0.47
    setVerticalGroup
    -0.47
    POSITIVE LOGITS
     avoient
    0.45
     enfans
    0.42
     pioggia
    0.40
    CrossRef
    0.40
     husband
    0.39
     dinner
    0.39
     hobby
    0.38
     baby
    0.37
    IsUnicode
    0.36
     _("
    0.36
    Activations Density 0.290%

    No Known Activations