© 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. 31-GEMMASCOPE-RES-16K
    6. 6113
    Prev
    Next
    INDEX
    Explanations

    tags related to categorization

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

    metadata tags or labels that categorize document content.

    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
    
    -0.34
    proken
    -0.33
     lược
    -0.32
     czemu
    -0.29
    ilon
    -0.29
     maisha
    -0.29
    s
    -0.29
     fact
    -0.28
    SneakyThrows
    -0.28
     rest
    -0.28
    POSITIVE LOGITS
     Tag
    0.93
     tag
    0.93
     tagName
    0.90
     TAG
    0.89
     tags
    0.89
     tagging
    0.84
    Tag
    0.83
     Tags
    0.82
    tag
    0.78
    TAG
    0.78
    Activations Density 0.103%

    No Known Activations