© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2489
    Prev
    Next
    INDEX
    Explanations

    football-related statistics and player evaluations

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

    improvements and progress

    np_acts-logits-general · gemini-2.0-flash

    promising preseason improvement

    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
     läßt
    -1.07
     idéia
    -1.04
     = 
    -0.99
     muß
    -0.98
     daß
    -0.94
     mußten
    -0.84
     Schluß
    -0.83
     definately
    -0.81
     mußte
    -0.79
     müßte
    -0.72
    POSITIVE LOGITS
     ⁠
    0.77
     TikTok
    0.76
     😅
    0.69
     COVID
    0.67
    ًا
    0.67
    https
    0.65
    めちゃくちゃ
    0.64
     🥲
    0.63
     macOS
    0.61
     👀
    0.61
    Activations Density 0.272%

    No Known Activations