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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 2733
    Prev
    Next
    INDEX
    Explanations

    references to people, social interactions, and exclusivity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rése
    -0.69
     esetben
    -0.56
     vastaan
    -0.54
     tárgy
    -0.54
     nélk
    -0.53
     kereszt
    -0.52
    éről
    -0.52
     helyzet
    -0.51
     felé
    -0.51
     sitä
    -0.51
    POSITIVE LOGITS
     Az
    0.73
    :✨
    0.71
     Ez
    0.66
     Minden
    0.65
     насељу
    0.64
     És
    0.60
    NUMX
    0.60
     Egy
    0.60
     Azt
    0.60
     Meg
    0.59
    Activations Density 0.041%

    No Known Activations