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. 18-GEMMASCOPE-RES-16K
    6. 5302
    Prev
    Next
    INDEX
    Explanations

    numerical values or mathematical expressions

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

    Appearing in or near mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical computations

    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
     DbType
    -0.71
    ↵↵↵↵↵
    -0.65
    <i>
    -0.63
    CURRENCY
    -0.63
    ◗
    -0.63
    GroupLayout
    -0.61
    <h6>
    -0.61
    CAPTION
    -0.61
     مفص
    -0.61
     onCancelled
    -0.60
    POSITIVE LOGITS
    UNRELATED
    0.72
    1
    0.70
     stamens
    0.69
     lys
    0.67
     Lilli
    0.66
    ıyors
    0.63
     Dalai
    0.63
     tann
    0.63
    ViewFeatures
    0.63
     bogotá
    0.61
    Activations Density 0.163%

    No Known Activations