© 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. 5575
    Prev
    Next
    INDEX
    Explanations

    phrases related to breaks and rest periods

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

    Short periods of rest or interruption

    np_acts-logits-general · gemini-2.0-flash

    breaks and pauses

    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
     schä
    -0.47
     amélior
    -0.47
    frontier
    -0.47
     strdup
    -0.46
     myö
    -0.46
    UrlEncoded
    -0.45
    ряда
    -0.44
     '{@
    -0.44
     charset
    -0.44
     perdana
    -0.43
    POSITIVE LOGITS
     break
    2.12
     breaks
    1.98
    break
    1.75
     Break
    1.66
     Breaks
    1.61
    breaks
    1.56
     BREAK
    1.52
    Break
    1.51
     intermission
    1.43
     pause
    1.38
    Activations Density 0.239%

    No Known Activations