© 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. 33-GEMMASCOPE-RES-16K
    6. 7273
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and symbols relevant to calculations and scientific discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.71
    dafx
    -0.71
    ftagPool
    -0.70
    DockStyle
    -0.69
    ConstraintMaker
    -0.69
    endphp
    -0.67
    ViewImports
    -0.66
    出版年
    -0.63
    Hozzáférés
    -0.62
     AssemblyProduct
    -0.59
    POSITIVE LOGITS
    −
    0.45
    ​
    0.40
    ∗
    0.38
     ​
    0.38
    andr
    0.37
    expliquer
    0.36
    Mr
    0.35
    Multi
    0.35
    Copy
    0.35
    ′
    0.34
    Activations Density 1.429%

    No Known Activations