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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9859
    Prev
    Next
    INDEX
    Explanations

    events and gatherings, particularly those associated with meetings, competitions, or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ész
    -0.50
    arão
    -0.48
    sbury
    -0.47
    ̀u
    -0.46
    peq
    -0.46
    ेशा
    -0.45
    unnitel
    -0.45
    meneu
    -0.44
    ViewInit
    -0.44
    itudinal
    -0.43
    POSITIVE LOGITS
     held
    2.13
    held
    1.75
     Held
    1.58
    Held
    1.54
     HELD
    1.50
     hold
    1.11
    hold
    1.02
     gehouden
    1.00
     hosted
    0.97
     Hold
    0.96
    Activations Density 0.154%

    No Known Activations