© 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. 18-GEMMASCOPE-RES-16K
    6. 6576
    Prev
    Next
    INDEX
    Explanations

    HTML form elements and their attributes

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

    HTML select options with a value

    np_acts-logits-general · gemini-2.0-flash

    option value attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QtCore
    -0.49
    $
    
    -0.48
     {}
    
    -0.48
    Vaata
    -0.48
    AutoresizingMask
    -0.47
    γο
    -0.47
    ::*;
    -0.47
     Ä
    -0.47
     />';
    -0.46
    eddable
    -0.46
    POSITIVE LOGITS
    GEBURTSDATUM
    0.73
    aarrggbb
    0.73
    /*---
    0.68
    HtmlAttribute
    0.67
    Personensuche
    0.66
     ब्रेकडाउन
    0.65
    verwijspagina
    0.63
     nakalista
    0.61
    expandindo
    0.61
     Roskov
    0.61
    Activations Density 0.079%

    No Known Activations