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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 4638
    Prev
    Next
    INDEX
    Explanations

    instances of the word "gather" and its variations, indicating a focus on collection or assembly contexts

    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
     Sinha
    -0.78
     Boeh
    -0.73
     Carlos
    -0.72
    λέον
    -0.71
     Edwards
    -0.68
     Meksiku
    -0.66
    <blockquote>
    -0.66
    Elvis
    -0.65
    aarrggbb
    -0.64
     Dietrich
    -0.63
    POSITIVE LOGITS
     Gather
    2.36
    Gather
    2.27
     Gathering
    2.15
     gathering
    2.12
     gathers
    2.10
     gather
    2.07
     gathered
    2.04
    Gathering
    2.01
    gathering
    1.94
    gather
    1.92
    Activations Density 0.084%

    No Known Activations