© 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. 1-GEMMASCOPE-RES-16K
    11. 8256
    Prev
    Next
    INDEX
    Explanations

    references to specific statistical distributions and their tests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -0.73
     initComponents
    -0.67
     HIEROGLYPH
    -0.67
     󰀄
    -0.67
     Beſ
    -0.64
     Anſ
    -0.64
     anonim
    -0.60
     ſame
    -0.60
    ↵↵
    -0.59
     tron
    -0.59
    POSITIVE LOGITS
     D
    1.52
     S
    1.45
     P
    1.44
     G
    1.44
     M
    1.43
     C
    1.41
     F
    1.40
     B
    1.39
     T
    1.38
     K
    1.37
    Activations Density 0.997%

    No Known Activations