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. 16-GEMMASCOPE-RES-16K
    6. 8979
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and data

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

    Numbers with decimals or exponents

    np_acts-logits-general · gemini-2.0-flash

    numerical measurements and data

    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
    Архівовано
    -0.70
    amsmath
    -0.64
     and
    -0.61
     the
    -0.55
     where
    -0.53
     оригіналу
    -0.53
    <eos>
    -0.52
    }})
    -0.52
    jica
    -0.52
     contextLoads
    -0.51
    POSITIVE LOGITS
     disambiguazione
    0.73
     propOrder
    0.70
     initComponents
    0.69
    complexContent
    0.67
    TagMode
    0.65
     auroit
    0.64
    tvguidetime
    0.63
     Picchu
    0.63
    AddHtmlAttribute
    0.63
     étoit
    0.61
    Activations Density 1.457%

    No Known Activations