© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6316
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically commas, in the text

    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
    iarkan
    -0.79
     Lichten
    -0.78
    hyr
    -0.78
     Thorne
    -0.72
     LIP
    -0.71
     Jayne
    -0.71
     Tann
    -0.69
    ')))
    -0.69
    ='';
    -0.69
     Asn
    -0.69
    POSITIVE LOGITS
    、
    1.22
    ،
    0.83
     、
    0.78
     frattempo
    0.74
    、、
    0.73
    、“
    0.71
     Chall
    0.71
    /...
    0.70
    PIX
    0.70
    )、
    0.69
    Activations Density 0.074%

    No Known Activations