© 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. 22-GEMMASCOPE-RES-16K
    11. 12708
    Prev
    Next
    INDEX
    Explanations

    expressions and words related to surprise or shock

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Japanese Hiragana "tsu" (つ, っ)

    np_acts-logits-general · gemini-2.0-flash

    Japanese emphatic sounds and mathematical symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.79
     N
    -0.78
     L
    -0.66
    os
    -0.65
     S
    -0.65
     R
    -0.65
     (
    -0.64
     K
    -0.63
     a
    -0.63
     H
    -0.62
    POSITIVE LOGITS
     Monfieur
    1.37
     Houſe
    1.35
     Theſe
    1.33
     myſelf
    1.30
     iſt
    1.27
     purpoſe
    1.27
     houſe
    1.26
     Jefus
    1.25
     auffi
    1.25
     ſind
    1.24
    Activations Density 0.085%

    No Known Activations