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. 11075
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal professionals and their qualifications

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

    past roles or history

    np_acts-logits-general · gemini-2.0-flash

    prior, previously, born, formerly

    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
    tagHelperRunner
    -0.68
     it
    -0.57
     scientists
    -0.53
    Scientists
    -0.53
     the
    -0.50
     namelijk
    -0.50
     nämlich
    -0.49
     Scientists
    -0.49
    因为它
    -0.49
    inguém
    -0.48
    POSITIVE LOGITS
     Prior
    1.03
    Prior
    0.97
     prior
    0.91
     Previously
    0.80
    Born
    0.80
     Born
    0.77
     Currently
    0.74
     Formerly
    0.73
     currently
    0.72
    Previously
    0.72
    Activations Density 0.222%

    No Known Activations