© 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. 15182
    Prev
    Next
    INDEX
    Explanations

    the presence of the sound "wh."

    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
    adaptiveStyles
    -0.84
    findpost
    -0.77
     disambiguazione
    -0.70
     onOptions
    -0.70
    PerformLayout
    -0.63
     Ber
    -0.63
    InputBorder
    -0.62
     Hartman
    -0.61
    layouts
    -0.60
     Irwin
    -0.59
    POSITIVE LOGITS
     wh
    3.65
    wh
    3.44
    Wh
    3.22
     Wh
    3.21
     WH
    2.72
    WH
    2.62
     Whiting
    1.45
    whi
    1.38
     whit
    1.37
     whi
    1.34
    Activations Density 0.081%

    No Known Activations