© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13117
    Prev
    Next
    INDEX
    Explanations

    code elements related to user interface components and layout management

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

    Often precedes math symbols or special characters

    np_acts-logits-general · gemini-2.0-flash

    mathematical context involving tokens like +, -, m, j

    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
    :✨
    -0.69
    Portail
    -0.69
    Personendaten
    -0.69
    HideFlags
    -0.68
     ISNI
    -0.67
    ThemeOverlay
    -0.63
    
    -0.61
     AssemblyCulture
    -0.59
    verwijspagina
    -0.59
    SourceChecksum
    -0.59
    POSITIVE LOGITS
     supposes
    0.60
    EndInit
    0.57
    esgue
    0.55
     SOB
    0.54
     CRL
    0.53
     Vesti
    0.53
     AGB
    0.52
     Dons
    0.52
     CIL
    0.51
     STRO
    0.51
    Activations Density 0.010%

    No Known Activations