Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 6126
    Prev
    Next
    INDEX
    Explanations

    references to sports and ball-related activities

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

    ball bounces and receptions

    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
     nahilalakip
    -0.47
     &___
    -0.35
     Савезне
    -0.34
    findpost
    -0.34
     pen
    -0.33
     CreateTagHelper
    -0.33
    )}_{
    -0.33
    }}_{
    -0.33
    IntOverflow
    -0.32
    出版年
    -0.32
    POSITIVE LOGITS
     فريبيس
    0.64
     bounce
    0.59
     bounces
    0.54
     Bounce
    0.54
     handleMessage
    0.52
    Bounce
    0.51
     receptions
    0.50
     cleanly
    0.49
     réception
    0.49
     touches
    0.48
    Activations Density 0.014%

    No Known Activations