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. 9-GEMMASCOPE-RES-16K
    6. 15310
    Prev
    Next
    INDEX
    Explanations

    references to mathematical models and stability conditions in complex systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.53
     Zuf
    -0.47
    ↵↵↵
    -0.46
     +
    -0.46
    <bos>
    -0.46
     потре
    -0.45
     tra
    -0.44
     ?
    -0.41
    REGISTER
    -0.40
    Buzz
    -0.40
    POSITIVE LOGITS
     '\\;'
    0.88
     مشين
    0.86
     protoimpl
    0.74
    UseVisualStyle
    0.71
    MessageTagHelper
    0.69
    abestanden
    0.68
     Audiodateien
    0.67
    WebServlet
    0.67
    Sucesor
    0.66
     zelve
    0.66
    Activations Density 1.161%

    No Known Activations