© 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. 8005
    Prev
    Next
    INDEX
    Explanations

    specific game expansions and their associated content

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

    alphanumeric identifiers and image URLs in structured data formats.

    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
    Synonymes
    -0.38
    cordova
    -0.35
     tavo
    -0.34
    
    -0.34
    mink
    -0.33
    IBOutlet
    -0.32
    MigrationBuilder
    -0.32
     ngang
    -0.32
    Sculpture
    -0.31
    iastes
    -0.30
    POSITIVE LOGITS
     cards
    1.10
     card
    1.03
    scryfall
    0.97
     Cards
    0.93
     decks
    0.91
     Card
    0.85
    カード
    0.84
     deck
    0.83
     TCG
    0.83
    cards
    0.82
    Activations Density 0.085%

    No Known Activations