Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1930
    Prev
    Next
    INDEX
    Explanations

    phrases related to layering or toppings in food descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.75
     RemoteException
    -0.53
     queſta
    -0.52
     الرياضيه
    -0.51
     liitty
    -0.49
    breakers
    -0.49
     ligiloj
    -0.48
     configureStore
    -0.48
    ylem
    -0.48
    ロウィン
    -0.47
    POSITIVE LOGITS
     overlay
    0.75
     encima
    0.69
     over
    0.64
    overlay
    0.63
     над
    0.62
     overlays
    0.61
     atop
    0.59
     OVER
    0.59
    Overlay
    0.58
     Overlay
    0.58
    Activations Density 0.886%

    No Known Activations