© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4876
    Prev
    Next
    INDEX
    Explanations

    questions or requests for assistance

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

    Following questions (starting with "can," "could," or "would")

    np_acts-logits-general · gemini-2.0-flash

    asking questions or requests

    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
    herself
    -0.59
    Chham
    -0.56
    ">—
    -0.56
     său
    -0.55
     denominado
    -0.53
    참고
    -0.52
    noopener
    -0.52
     sendiri
    -0.51
    تفصیلات
    -0.50
     pinulongan
    -0.50
    POSITIVE LOGITS
     they
    1.64
     we
    1.48
     anyone
    1.32
     anybody
    1.20
     you
    1.16
     someone
    0.97
     it
    0.97
    anyone
    0.93
     I
    0.93
     there
    0.93
    Activations Density 0.118%

    No Known Activations