© 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. 14458
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to functions and their properties

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

    Greek letters and mathematical symbols in equations, particularly alpha, lambda, and other parameters in formulas.

    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
    findpost
    -0.59
    ParallelGroup
    -0.55
    awin
    -0.51
     '\\;'
    -0.45
     utafitiHapana
    -0.45
     חיצוניים
    -0.43
     onItemClick
    -0.42
    ox
    -0.42
    aults
    -0.42
    objec
    -0.40
    POSITIVE LOGITS
    質
    0.47
    fromnode
    0.40
    WebServlet
    0.36
    InjectMocks
    0.36
    enapa
    0.36
    enderror
    0.35
     iconTwitter
    0.35
    Fraction
    0.35
    typeorm
    0.35
    质
    0.35
    Activations Density 1.431%

    No Known Activations