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. 5-GEMMASCOPE-RES-16K
    6. 12002
    Prev
    Next
    INDEX
    Explanations

    terms related to gathering or accumulating information and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.76
     ré
    -0.55
    dtos
    -0.54
    檔
    -0.52
     yii
    -0.52
     Ord
    -0.52
    Weblinks
    -0.51
    phorbia
    -0.50
     Christensen
    -0.50
     déf
    -0.50
    POSITIVE LOGITS
     Collect
    2.11
    collect
    2.08
    Collect
    2.03
     Collecting
    1.99
     collects
    1.99
     collecting
    1.98
     collect
    1.98
     collected
    1.95
    Collecting
    1.93
    COLLECT
    1.92
    Activations Density 0.092%

    No Known Activations