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. 6-GEMMASCOPE-RES-16K
    6. 448
    Prev
    Next
    INDEX
    Explanations

    instances of jQuery or related function calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تانيه
    -0.75
     متعلقه
    -0.72
    المناصب
    -0.68
     banho
    -0.66
     الرياضيه
    -0.62
    AndEndTag
    -0.62
     nakalista
    -0.60
     defStyle
    -0.60
     morire
    -0.60
    inorder
    -0.59
    POSITIVE LOGITS
    ($(
    1.30
    $(
    1.06
     ($(
    1.06
    ="$(
    1.04
    =$(
    0.93
     $(
    0.92
     Searle
    0.86
    RectangleBorder
    0.77
    ".
    
    0.75
    glomer
    0.75
    Activations Density 0.075%

    No Known Activations