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. 21-GEMMASCOPE-RES-16K
    6. 7531
    Prev
    Next
    INDEX
    Explanations

    messages related to errors and confirmations in user interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.56
     when
    -0.41
    よる
    -0.41
    zzly
    -0.41
    を見ながら
    -0.41
    setAccessible
    -0.40
    Weblinks
    -0.40
    自然是
    -0.40
     hablado
    -0.38
    ObjectMeta
    -0.38
    POSITIVE LOGITS
     please
    1.07
     sorry
    1.04
    please
    1.01
     Please
    0.98
    sorry
    0.98
     Sorry
    0.95
    Please
    0.93
    Sorry
    0.90
     SORRY
    0.88
     Veuillez
    0.86
    Activations Density 0.110%

    No Known Activations