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. 4-GEMMASCOPE-RES-16K
    6. 15938
    Prev
    Next
    INDEX
    Explanations

    HTML table elements and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ielle
    -0.56
    Eden
    -0.54
     saites
    -0.54
     Eden
    -0.52
    щь
    -0.52
     sessionFactory
    -0.52
     yang
    -0.51
    сылкі
    -0.51
    ỡng
    -0.50
     I
    -0.50
    POSITIVE LOGITS
    <table>
    4.41
    </table>
    1.44
    <caption>
    1.21
    tabular
    1.08
    /**
    1.04
    </caption>
    1.01
    ={`/
    0.96
    table
    0.94
    <h5>
    0.93
    <h6>
    0.91
    Activations Density 0.066%

    No Known Activations