Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 780
    Prev
    Next
    INDEX
    Explanations

    HTML elements and structure, particularly related to spans, divs, and button attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.89
     autorytatywna
    -0.79
    تقاوى
    -0.71
    MessageOf
    -0.71
    findpost
    -0.68
     snippetHide
    -0.66
     beginnetje
    -0.64
    Identyfik
    -0.64
     tartalomajánló
    -0.63
    ValueStyle
    -0.63
    POSITIVE LOGITS
    endphp
    0.66
     arşivlendi
    0.64
    WebControls
    0.55
     šķ
    0.54
     but
    0.53
    WritableDatabase
    0.53
     COMMENTS
    0.51
    pagestyle
    0.51
    Искәрмәләр
    0.49
    closePath
    0.49
    Activations Density 0.961%

    No Known Activations