© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8296
    Prev
    Next
    INDEX
    Explanations

    opening and closing braces in mathematical or programming contexts

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

    LaTeX formatting, especially matrices and arrays

    np_acts-logits-general · gemini-2.0-flash

    mathematical array and alignment environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -1.05
     المعيارى
    -0.99
     nakalista
    -0.99
    AndEndTag
    -0.90
    цездатний
    -0.89
    GEBURTSDATUM
    -0.89
     mergeFrom
    -0.88
    WebElementEntity
    -0.85
    oredCriteria
    -0.84
    libft
    -0.83
    POSITIVE LOGITS
    CJK
    0.52
    center
    0.48
    再来
    0.47
     Kinders
    0.47
    itemize
    0.45
     Coronado
    0.45
    enumerate
    0.45
     linearized
    0.42
    *[
    0.41
     Eurovision
    0.41
    Activations Density 0.013%

    No Known Activations