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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 13-GEMMASCOPE-RES-16K
    6. 12295
    Prev
    Next
    INDEX
    Explanations

    references to constructor methods in code documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.95
     المعيارى
    -0.91
    findpost
    -0.88
    '));
    
    -0.79
    .';
    -0.79
     Garnet
    -0.76
    MessageTagHelper
    -0.75
    expandindo
    -0.75
     Shee
    -0.74
    دانشنامهٔ
    -0.74
    POSITIVE LOGITS
    <th>
    2.17
     (“
    0.76
    、“
    0.74
    {{\
    0.74
    ={`${
    0.74
     Ather
    0.73
    ormick
    0.73
    (“
    0.73
    、【
    0.72
    vgili
    0.72
    Activations Density 0.017%

    No Known Activations