© 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. 21-GEMMASCOPE-RES-16K
    6. 13785
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and comments on experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HttpNotFound
    -0.61
     therefore
    -0.57
    WebVitals
    -0.55
     Wikiseite
    -0.54
    adaptiveStyles
    -0.52
    memoized
    -0.52
     useAppContext
    -0.52
     wikipagina
    -0.51
    كويكب
    -0.51
    AntiForgeryToken
    -0.49
    POSITIVE LOGITS
     kasarigan
    0.42
    lasser
    0.37
     resourceCulture
    0.36
    migrationBuilder
    0.35
    deckt
    0.32
    niew
    0.31
    Collegamenti
    0.31
    ram
    0.31
    xFFFF
    0.30
    一来
    0.30
    Activations Density 0.404%

    No Known Activations