© 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. 24-GEMMASCOPE-RES-16K
    11. 8378
    Prev
    Next
    INDEX
    Explanations

    HTML elements and buttons in a web document

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

    HTML tags and properties

    np_acts-logits-general · gemini-2.0-flash

    tags with attributes or code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bės
    -0.53
     New
    -0.50
     m
    -0.45
    <eos>
    -0.44
    m
    -0.44
    ster
    -0.43
    stris
    -0.43
     application
    -0.42
    ze
    -0.42
    anzi
    -0.42
    POSITIVE LOGITS
    BindingResult
    0.96
    mybatisplus
    0.94
    adaptiveStyles
    0.93
    principalColumn
    0.92
     ComVisible
    0.82
    HtmlAttribute
    0.79
    GEBURTSDATUM
    0.77
    HandlerContext
    0.77
    aarrggbb
    0.76
    ThroughAttribute
    0.75
    Activations Density 0.025%

    No Known Activations