© 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. 20-GEMMASCOPE-RES-16K
    6. 14196
    Prev
    Next
    INDEX
    Explanations

    terms related to filtering and selection processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code or UI elements related to filtering data or search functionality.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newName
    -0.77
     newState
    -0.60
    setVerticalGroup
    -0.58
    newName
    -0.57
     Coy
    -0.56
    posedge
    -0.55
     userName
    -0.54
     CGPoint
    -0.54
    Shawn
    -0.54
     requestId
    -0.54
    POSITIVE LOGITS
     filter
    1.40
    filter
    1.36
     Filter
    1.30
    Filter
    1.22
     FILTER
    1.17
    FILTER
    1.13
     filters
    1.09
     filtre
    1.07
     Filters
    1.05
    filters
    1.03
    Activations Density 0.075%

    No Known Activations