© 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. 39-GEMMASCOPE-RES-16K
    6. 1586
    Prev
    Next
    INDEX
    Explanations

    military-related terms and concepts, particularly those associated with operations and training phases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.59
     îns
    -0.47
     utafitiHapana
    -0.41
    ANNELS
    -0.38
     sanguí
    -0.37
    WithMany
    -0.37
     množství
    -0.36
    LookAnd
    -0.36
     parrilla
    -0.35
     mourut
    -0.34
    POSITIVE LOGITS
     craft
    0.65
    craft
    0.63
     ops
    0.62
    crafts
    0.60
     Craft
    0.59
     OPS
    0.58
     crafts
    0.57
    autique
    0.56
     Ops
    0.56
     operations
    0.55
    Activations Density 0.585%

    No Known Activations