Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1743
    Prev
    Next
    INDEX
    Explanations

    mathematical formatting and structure in documents, particularly in relation to tables and equations

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

    LaTeX math expressions (equation environments)

    np_acts-logits-general · gemini-2.0-flash

    array environments

    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
    ::~
    -0.91
     /\.(
    -0.88
    تقاوى
    -0.85
    @[+][
    -0.78
    Vidite
    -0.74
    ScopeManager
    -0.73
    ⓧ
    -0.71
    ={`/
    -0.71
    (&:
    -0.70
    Geplaatst
    -0.69
    POSITIVE LOGITS
     Saltar
    0.47
    illoin
    0.46
    usermodel
    0.45
     magasiner
    0.44
     presentato
    0.41
    TargetException
    0.41
     cardinals
    0.40
    polate
    0.40
    Partager
    0.39
    <tr>
    0.39
    Activations Density 0.071%

    No Known Activations