© 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. 6105
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with a specific location or entity, particularly related to "Wyoming."

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

    proper nouns and place names, particularly those starting with "Wy" (like Wyoming, Wycombe, Wyclef).

    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
     propOrder
    -0.54
    spheric
    -0.43
     Soft
    -0.42
    resizingMask
    -0.41
    lt
    -0.41
     BoxFit
    -0.41
    ent
    -0.41
     Subject
    -0.41
    ciąg
    -0.41
    oft
    -0.41
    POSITIVE LOGITS
     utafitiHapana
    0.50
     ***!
    0.46
     pintadas
    0.45
     surla
    0.44
     wy
    0.44
    ChildScrollView
    0.42
     Enviar
    0.42
     Menjadi
    0.41
     IBOutlet
    0.40
     @"/
    0.40
    Activations Density 0.023%

    No Known Activations