© 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. 31-GEMMASCOPE-RES-16K
    6. 5167
    Prev
    Next
    INDEX
    Explanations

    punctuation and rhetorical questioning in the text

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

    exclamatory sentences and emphatic expressions of surprise or realization.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.63
     linkovi
    -0.56
     AssemblyCulture
    -0.55
     EconPapers
    -0.55
    
    -0.52
     wireType
    -0.45
     مشين
    -0.44
    exitRule
    -0.44
    WireFormatLite
    -0.42
     estekak
    -0.41
    POSITIVE LOGITS
     oh
    1.88
     Oh
    1.77
     Wow
    1.74
     wow
    1.73
    Oh
    1.65
    Wow
    1.61
    wow
    1.48
    oh
    1.42
     Ooh
    1.40
     WOW
    1.38
    Activations Density 0.270%

    No Known Activations