© 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. 12-GEMMASCOPE-RES-16K
    6. 12555
    Prev
    Next
    INDEX
    Explanations

    terms related to filtering data or selections in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imageName
    -0.56
     newName
    -0.53
     newState
    -0.53
     isSuccess
    -0.49
     newUser
    -0.49
     testCase
    -0.46
    ACTUAL
    -0.46
     xPos
    -0.44
     productName
    -0.44
    createCell
    -0.43
    POSITIVE LOGITS
     filter
    2.08
     Filter
    1.91
    filter
    1.90
     FILTER
    1.75
    Filter
    1.75
     filters
    1.73
     Filters
    1.62
     filtering
    1.61
    FILTER
    1.61
     filtre
    1.54
    Activations Density 0.157%

    No Known Activations