© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 36595
    Prev
    Next
    INDEX
    Explanations

    elements related to properties, efficacy, and compatibility within various contexts

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

    technical nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     instead
    -0.72
    instead
    -0.70
     además
    -0.69
     Instead
    -0.66
    だけでなく
    -0.63
    而不是
    -0.63
    뿐
    -0.63
     although
    -0.62
     ainsi
    -0.61
    although
    -0.61
    POSITIVE LOGITS
     semuanya
    0.50
     Normdatei
    0.43
    principalTable
    0.43
     nữa
    0.42
     thrown
    0.42
     ikut
    0.42
     turut
    0.39
     keduanya
    0.39
     tudo
    0.39
    makeText
    0.39
    Activations Density 0.091%

    No Known Activations