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. 13398
    Prev
    Next
    INDEX
    Explanations

    phrases indicating transitions or changes in status, particularly related to departures and organizational shifts

    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
    tagHelperRunner
    -0.60
     overcoming
    -0.56
     Waray
    -0.56
    ıklı
    -0.56
    sizeCache
    -0.53
     saites
    -0.52
    ükemmel
    -0.52
    κης
    -0.52
    @[+][
    -0.52
     tiennent
    -0.51
    POSITIVE LOGITS
     replaced
    1.15
     leaving
    0.97
    replaced
    0.93
     Replaced
    0.90
    leaving
    0.88
     laissant
    0.85
    只剩下
    0.81
     replacement
    0.77
     laisse
    0.77
    代わりに
    0.76
    Activations Density 0.393%

    No Known Activations