© 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. 13633
    Prev
    Next
    INDEX
    Explanations

    HTML attributes related to button styles and properties

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

    Tokens preceding "primary" or "default" in HTML button classes

    np_acts-logits-general · gemini-2.0-flash

    bootstrapped button classes

    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
    IndentedString
    -0.69
    CloseOperation
    -0.68
    enumi
    -0.65
    DebuggerNonUser
    -0.61
    oneofs
    -0.58
    cshtml
    -0.57
    setAccessible
    -0.55
    urlpatterns
    -0.55
    LookAnd
    -0.54
    ffffffff
    -0.53
    POSITIVE LOGITS
    primary
    0.99
     primary
    0.90
    danger
    0.87
    success
    0.81
     danger
    0.80
     Primary
    0.78
    Primary
    0.73
     success
    0.73
     PRIMARY
    0.72
    warning
    0.72
    Activations Density 0.083%

    No Known Activations