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. 15648
    Prev
    Next
    INDEX
    Explanations

    phrases involving conjunctions and connection between ideas

    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
    tvguidetime
    -0.83
    richTextPanel
    -0.77
     disambiguazione
    -0.74
    ^(@)
    -0.74
    RenderAtEndOf
    -0.73
     invokingState
    -0.72
    <tfoot>
    -0.72
    bootstrapcdn
    -0.71
    EndProject
    -0.70
     snippetHide
    -0.70
    POSITIVE LOGITS
     appunto
    0.55
    ↵↵↵
    0.53
    .
    0.52
    etc
    0.48
    .\\
    0.46
     جغرافيا
    0.45
    dd
    0.44
     ActionBar
    0.44
     ди
    0.43
    ple
    0.43
    Activations Density 0.670%

    No Known Activations