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. 22-GEMMASCOPE-RES-16K
    6. 12988
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their actions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "was" or "were"

    np_acts-logits-general · gemini-2.0-flash

    was verb-ing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ativa
    -0.55
    prototype
    -0.54
    вня
    -0.52
    ActionResult
    -0.49
     liknande
    -0.49
    بوابة
    -0.49
     aprendido
    -0.48
     bụ
    -0.48
    izr
    -0.47
    PasswordEncoder
    -0.47
    POSITIVE LOGITS
     sedang
    0.92
     preparing
    0.92
     initComponents
    0.78
    preparing
    0.77
     đang
    0.76
     Paglinawan
    0.75
     standing
    0.75
     autorytatywna
    0.75
     tengah
    0.73
    Preparing
    0.73
    Activations Density 0.289%

    No Known Activations