© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13775
    Prev
    Next
    INDEX
    Explanations

    words related to clothing and exercises

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

    "exercise", "clothes", or "injured/illness"

    np_acts-logits-general · gemini-2.0-flash

    exercise and health issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ponta
    -0.53
     Oka
    -0.48
     Tera
    -0.47
     Impact
    -0.45
     Peak
    -0.44
    detectChanges
    -0.42
     Spector
    -0.41
     Aurora
    -0.41
     IMPACT
    -0.41
     Stellar
    -0.40
    POSITIVE LOGITS
    Clothes
    0.66
     myſelf
    0.65
    Exercise
    0.62
     EXERCISE
    0.61
     Reſ
    0.61
    zzleHttp
    0.60
     Exercise
    0.60
    nastics
    0.60
     Clothes
    0.59
    clothing
    0.58
    Activations Density 0.395%

    No Known Activations