© 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. 2777
    Prev
    Next
    INDEX
    Explanations

    emphasis on large quantities or significant challenges

    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
     виправивши
    -0.58
     virkelig
    -0.56
     real
    -0.55
     verdaderas
    -0.55
     guère
    -0.53
     tikra
    -0.50
     absolute
    -0.50
     略
    -0.50
     verdaderos
    -0.49
     riktig
    -0.48
    POSITIVE LOGITS
     متعلقه
    0.83
     للاسماء
    0.79
    aarrggbb
    0.73
     deal
    0.70
     "..\..\
    0.69
     relief
    0.67
     help
    0.66
    Хьажоргаш
    0.65
    fromnode
    0.64
     advantage
    0.64
    Activations Density 0.240%

    No Known Activations