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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 2857
    Prev
    Next
    INDEX
    Explanations

    information related to protests and activism, particularly focused on social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    లాలు
    -0.69
     виправивши
    -0.59
    ỡng
    -0.57
     חיצוניים
    -0.56
    inheritDoc
    -0.56
    Datuak
    -0.56
    ribadian
    -0.54
     समीक्षाओं
    -0.54
    kulum
    -0.54
     preferencia
    -0.54
    POSITIVE LOGITS
     petition
    0.90
     activist
    0.84
     campaign
    0.83
     activists
    0.82
     Petition
    0.80
     advocacy
    0.80
     campaigned
    0.78
     campaigning
    0.78
     petitions
    0.73
     activism
    0.73
    Activations Density 0.458%

    No Known Activations