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. 3182
    Prev
    Next
    INDEX
    Explanations

    specific variable names and their associated numeric values or identifiers in code or mathematical contexts

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

    Starts with a non-alphanumeric character

    np_acts-logits-general · gemini-2.0-flash

    square lattices

    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
     للاسماء
    -0.55
     onCreateView
    -0.51
     cref
    -0.50
    CloseOperation
    -0.49
     ripening
    -0.49
     @}
    -0.49
     Nuss
    -0.48
     Appearance
    -0.48
     flamme
    -0.48
     Friedens
    -0.48
    POSITIVE LOGITS
    ArrowToggle
    0.74
    AsUp
    0.59
    theless
    0.58
    ыгана
    0.57
     iconLine
    0.55
     بيها
    0.54
     Вікіпе
    0.53
    Personensuche
    0.53
     varargin
    0.52
    انجليز
    0.52
    Activations Density 0.466%

    No Known Activations