© 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. 11688
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific structured data elements

    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
     using
    -0.27
     principle
    -0.25
     mess
    -0.25
     offensive
    -0.24
     pr
    -0.24
    Query
    -0.23
     query
    -0.23
     nhật
    -0.23
     sl
    -0.23
    mate
    -0.22
    POSITIVE LOGITS
    AndEndTag
    0.90
     ब्रेकडाउन
    0.77
     ExecuteAsync
    0.77
    WithIOException
    0.76
    CodedInputStream
    0.75
     noDo
    0.72
    transQ
    0.71
     للمعارف
    0.71
     ModelExpression
    0.70
     Exacts
    0.69
    Activations Density 1.858%

    No Known Activations