© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 91484
    Prev
    Next
    INDEX
    Explanations

    phrases that describe affiliations or characteristics of entities

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

    of sorts

    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
    怎麼辦
    -0.30
     Fiona
    -0.29
    fileName
    -0.29
    muka
    -0.28
     Cas
    -0.28
     Kle
    -0.28
     Kluwer
    -0.28
     Rama
    -0.27
    nodeId
    -0.27
     horaires
    -0.27
    POSITIVE LOGITS
     sorts
    2.20
     sort
    1.84
    sort
    1.69
     Sort
    1.49
     sorta
    1.40
    Sort
    1.34
     SORT
    1.30
     sortes
    1.21
     sorte
    1.07
     kind
    1.05
    Activations Density 0.081%

    No Known Activations