© 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-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10532
    Prev
    Next
    INDEX
    Explanations

    instances of the word "say" and its variations, indicating expressions of speech or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -1.02
     المعيارى
    -0.98
    ."));
    -0.92
    StoryboardSegue
    -0.92
    .";
    
    -0.89
    ReusableCell
    -0.88
     كومونز
    -0.86
    InjectAttribute
    -0.85
    ."),
    -0.85
    .",
    
    -0.84
    POSITIVE LOGITS
     say
    2.70
    say
    2.31
     Say
    2.17
    Say
    2.08
     SAY
    1.98
     says
    1.86
    SAY
    1.76
    says
    1.46
     Says
    1.40
     saying
    1.34
    Activations Density 0.046%

    No Known Activations