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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6162
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and formatting elements in text

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

    mathematical notation and symbols, particularly LaTeX formatting and mathematical equations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    LaTeX math-mode formatting and alignment syntax, especially equation environment delimiters, spacing, and line-break commands.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    line breaks and indentation in mathematical LaTeX equations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.64
    protoimpl
    -0.52
     CanadaChoose
    -0.47
     咖
    -0.45
    Datuak
    -0.44
     againſt
    -0.44
     toont
    -0.43
    RTN
    -0.43
    libft
    -0.43
     Dalton
    -0.43
    POSITIVE LOGITS
    RegressionTest
    0.42
    DockStyle
    0.42
    SharedDtor
    0.40
    extAlignment
    0.40
     aikana
    0.40
    TagHelper
    0.39
    EndContext
    0.39
    })*/
    0.38
    }*/
    0.36
    NavController
    0.36
    Activations Density 0.269%

    No Known Activations