© 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. 13683
    Prev
    Next
    INDEX
    Explanations

    structured data elements and their attributes

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

    commas that appear after quoted strings or variable names in code and configuration contexts.

    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
     المعيارى
    -0.82
     wireType
    -0.72
    niſſe
    -0.70
    yntaxException
    -0.69
     laſſen
    -0.69
     betweenstory
    -0.68
     '/';
    -0.68
     $_(
    -0.67
    RTEX
    -0.66
     queſta
    -0.66
    POSITIVE LOGITS
     "
    1.30
     “
    1.27
    「
    1.15
    “
    1.02
     „
    0.96
     «
    0.91
     '
    0.86
    "
    0.80
     ”
    0.78
     \"
    0.75
    Activations Density 0.373%

    No Known Activations