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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 2985
    Prev
    Next
    INDEX
    Explanations

    references to injuries and game-related events

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

    Occurrences in the first or second half/quarter

    np_acts-logits-general · gemini-2.0-flash

    halftime

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.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
    İstinadlar
    -0.61
    uxxxx
    -0.58
    AutoScaleMode
    -0.55
    Styleable
    -0.52
     perdana
    -0.52
    aronder
    -0.50
     chaining
    -0.49
    MENAFN
    -0.48
    Öffnungszeiten
    -0.48
     "..\..\..\
    -0.47
    POSITIVE LOGITS
     halftime
    1.51
     intermission
    1.18
    Half
    1.05
     half
    1.04
    HALF
    1.00
     Half
    0.99
    half
    0.94
     Halb
    0.94
     interval
    0.93
     HALF
    0.90
    Activations Density 0.100%

    No Known Activations