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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5380
    Prev
    Next
    INDEX
    Explanations

    punctuation and dialogue markers in conversations

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

    Follows conversational punctuation

    np_acts-logits-general · gemini-2.0-flash

    contextual interjections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.55
    aarrggbb
    -0.50
    Története
    -0.48
    ViewFeatures
    -0.47
    ]>=
    -0.47
    ]?.
    -0.47
    freep
    -0.47
    andaag
    -0.45
    ]<=
    -0.44
    RegressionTest
    -0.43
    POSITIVE LOGITS
     Well
    1.02
    Well
    1.01
    Really
    0.99
     Really
    0.96
     well
    0.92
     huh
    0.89
    Huh
    0.87
    是吗
    0.86
    Oh
    0.86
     Interesting
    0.85
    Activations Density 0.125%

    No Known Activations