© 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. 7432
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential or significance in research findings

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

    phrases expressing potential or capability using "has" followed by words like "potential," "a," or descriptive terms.

    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
    rungsseite
    -0.57
     AssemblyCompany
    -0.56
    ſelves
    -0.52
    MessageOf
    -0.52
     bershka
    -0.48
    entyfik
    -0.47
    ptonshire
    -0.47
    ➯
    -0.46
    parsedMessage
    -0.46
    abases
    -0.46
    POSITIVE LOGITS
     been
    0.67
     relevance
    0.63
     significance
    0.58
     implications
    0.55
     potential
    0.52
    potential
    0.49
     connotations
    0.49
     become
    0.48
     merit
    0.48
     similarities
    0.48
    Activations Density 0.484%

    No Known Activations