© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15937
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols commonly used in academia

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

    mathematical notation and variables following "\mathbf" in LaTeX equations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Tikang
    -0.67
     препратки
    -0.58
    AndEndTag
    -0.57
    躇
    -0.56
     nahilalakip
    -0.53
     <=",
    -0.53
    tagHelperRunner
    -0.52
    include
    -0.52
     Segovia
    -0.50
     MainAxisSize
    -0.50
    POSITIVE LOGITS
    mathbf
    1.55
    boldsymbol
    0.87
    <b>
    0.69
    <strong>
    0.69
    er
    0.67
    mathcal
    0.57
    mathbb
    0.56
    textbf
    0.56
     băr
    0.51
    mathfrak
    0.48
    Activations Density 0.224%

    No Known Activations