© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 10233
    Prev
    Next
    INDEX
    Explanations

    references to distractions and the impact they have on focus or performance

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

    distraction and diversion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    haikusbot
    -0.46
     gynhyrchwyd
    -0.44
    RTLU
    -0.44
     NSCoder
    -0.43
    WebServlet
    -0.42
     صوتيه
    -0.42
    忑
    -0.40
     neer
    -0.40
    Nationalité
    -0.40
    Twig
    -0.38
    POSITIVE LOGITS
     distraction
    2.61
     distractions
    2.45
     distract
    2.41
     distracting
    2.38
     distra
    2.36
     distracted
    2.30
     Distra
    2.14
     diversion
    1.92
     divert
    1.82
     diversions
    1.79
    Activations Density 0.150%

    No Known Activations