© 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. 31-GEMMASCOPE-RES-16K
    11. 13123
    Prev
    Next
    INDEX
    Explanations

    commands related to ending sections or environments in a markup language (such as LaTeX)

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

    LaTeX document structure commands and environment declarations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.47
    principalColumn
    -0.47
     gynhyrchwyd
    -0.47
    nloa
    -0.44
    utilisons
    -0.44
    readAs
    -0.42
    jspb
    -0.42
    GEBURTS
    -0.41
    Personendaten
    -0.40
    glas
    -0.39
    POSITIVE LOGITS
     center
    0.79
     centre
    0.75
    center
    0.69
     Center
    0.65
    centre
    0.65
     CENTER
    0.65
     centro
    0.64
     centrum
    0.62
    CENTER
    0.62
    Center
    0.61
    Activations Density 0.013%

    No Known Activations