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. 20-GEMMASCOPE-RES-16K
    6. 45
    Prev
    Next
    INDEX
    Explanations

    indicators of medical conditions and pregnancy-related terms

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

    a positive turn of events

    np_acts-logits-general · gemini-2.0-flash

    relief after waiting

    np_acts-logits-general · gemini-2.5-flash-lite

    The marked tokens represent short phrases, clauses, and single words that serve as logical break points in narrative flow—typically at sentence boundaries, clause transitions, or between independent thoughts. These include period punctuation, conjunctions, prepositions introducing new clauses, and noun phrases that mark shifts in time, location, or topic within casual blog-style prose and personal narratives.

    eleuther_acts_top20 · claude-4-5-haikuTriggered by @kparkhamchuk
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    your
    -0.75
     your
    -0.75
     Monthly
    -0.68
    あなたが
    -0.68
     you
    -0.66
    あなた
    -0.66
     jährlich
    -0.66
     annually
    -0.66
    出版年
    -0.65
     vaak
    -0.64
    POSITIVE LOGITS
     luckily
    0.77
     Luckily
    0.72
     finally
    0.71
     surprisingly
    0.70
     thankfully
    0.69
    Luckily
    0.69
     fortunately
    0.68
     Surprisingly
    0.67
    早速
    0.66
    Surprisingly
    0.66
    Activations Density 0.314%

    No Known Activations