© 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. 10-GEMMASCOPE-RES-16K
    6. 8419
    Prev
    Next
    INDEX
    Explanations

    specific LaTeX package commands and symbols related to mathematics and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yks
    -0.40
    Controls
    -0.33
     kiin
    -0.32
    '&:
    -0.32
     lähe
    -0.32
    ionView
    -0.32
    esehen
    -0.31
     登
    -0.31
    kaufs
    -0.31
    arnya
    -0.30
    POSITIVE LOGITS
    CodeAttribute
    6.06
    GeneratedCode
    1.20
    CodeDom
    1.14
    httphttps
    0.94
    ValueStyle
    0.82
    IsContent
    0.81
    DebuggerNonUser
    0.80
    HasAnnotation
    0.79
    ThroughAttribute
    0.79
    disposing
    0.77
    Activations Density 0.021%

    No Known Activations