© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8657
    Prev
    Next
    INDEX
    Explanations

    punctuation and its variations within the context of written material

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favorably
    -0.78
     honored
    -0.77
     theater
    -0.77
     coloring
    -0.77
     COLOR
    -0.75
     Coloring
    -0.75
    Theater
    -0.75
     theaters
    -0.74
     honors
    -0.74
     vapors
    -0.74
    POSITIVE LOGITS
     summarised
    0.95
     centralised
    0.94
     ExecuteAsync
    0.91
    personalised
    0.89
     organisations
    0.87
    itisation
    0.87
    ategorised
    0.85
    )");
    
    0.85
    alised
    0.85
     standardised
    0.84
    Activations Density 0.068%

    No Known Activations