© 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. 22-GEMMASCOPE-RES-16K
    6. 14980
    Prev
    Next
    INDEX
    Explanations

    programming-related concepts and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyrchwyd
    -0.42
     مشين
    -0.40
    forChild
    -0.37
    JspWriter
    -0.34
     excellent
    -0.33
     recommending
    -0.33
    RTSN
    -0.32
    MigrationBuilder
    -0.31
    براير
    -0.31
     str
    -0.30
    POSITIVE LOGITS
     Monfieur
    0.52
     mijne
    0.50
     coleção
    0.47
     zijne
    0.47
    wapV
    0.45
    "/",
    0.45
     otomatig
    0.44
     cappello
    0.44
    luigi
    0.44
     queſta
    0.43
    Activations Density 0.563%

    No Known Activations