© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14710
    Prev
    Next
    INDEX
    Explanations

    key statistics and achievements related to sports performances

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

    Winning streaks or surges in sports

    np_acts-logits-general · gemini-2.0-flash

    streak of success

    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
    apimachinery
    -0.73
     kasarigan
    -0.63
     ujednoznacz
    -0.58
    EndGlobalSection
    -0.53
    acamata
    -0.53
    tonsoft
    -0.53
    Atsauces
    -0.51
     estri
    -0.50
    phrag
    -0.49
     UIKit
    -0.48
    POSITIVE LOGITS
     streak
    1.19
     run
    1.04
     string
    1.01
     stretch
    0.95
    streak
    0.91
     streaks
    0.90
     hot
    0.88
     momentum
    0.76
     spurt
    0.76
     STRE
    0.76
    Activations Density 0.138%

    No Known Activations