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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 15042
    Prev
    Next
    INDEX
    Explanations

    statements related to coaching and player dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.69
    ImageContext
    -0.68
    SequentialGroup
    -0.66
    ंदीखरीदारी
    -0.64
     touristes
    -0.61
     préc
    -0.61
    EDEFAULT
    -0.59
     ContentValues
    -0.57
    церт
    -0.56
     illustrazione
    -0.56
    POSITIVE LOGITS
     coaching
    0.90
     coaches
    0.87
     coached
    0.86
     coach
    0.78
    Coaching
    0.72
     Coaching
    0.72
     Coach
    0.71
     Coaches
    0.67
    coaching
    0.64
    Coaches
    0.61
    Activations Density 0.179%

    No Known Activations