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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 6326
    Prev
    Next
    INDEX
    Explanations

    lines of code that involve manipulation of element styles and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ivelany
    -0.56
    aarrggbb
    -0.51
     linkovi
    -0.47
     Occupations
    -0.47
    SequentialGroup
    -0.45
    +#+
    -0.45
    richTextPanel
    -0.44
    ">—
    -0.43
    DataPropertyName
    -0.42
    ubri
    -0.42
    POSITIVE LOGITS
     disponibilités
    0.69
     sitten
    0.63
    tagHelperRunner
    0.61
    ViewFeatures
    0.57
     صوتيه
    0.56
     navideñas
    0.56
    Skocz
    0.56
     snippetHide
    0.55
    λίου
    0.55
     standardize
    0.54
    Activations Density 0.268%

    No Known Activations