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. 16-GEMMASCOPE-RES-16K
    6. 15811
    Prev
    Next
    INDEX
    Explanations

    references to economic and societal issues related to inequality and competition

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

    Follows intensifiers such as "so" and "such"

    np_acts-logits-general · gemini-2.0-flash

    high quantity or degree

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    timis
    -0.44
     onBind
    -0.42
    otto
    -0.40
     kip
    -0.39
     Core
    -0.39
     Winaray
    -0.38
    LookAnd
    -0.38
     tiros
    -0.38
    ar
    -0.38
    이는
    -0.37
    POSITIVE LOGITS
     tantas
    1.06
     tantos
    1.04
     begitu
    1.03
     so
    1.01
     tellement
    0.88
    这么多
    0.86
     इत
    0.85
     zoveel
    0.84
     så
    0.83
     tão
    0.82
    Activations Density 0.164%

    No Known Activations