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. 38-GEMMASCOPE-RES-16K
    6. 13365
    Prev
    Next
    INDEX
    Explanations

    descriptions of amusement parks and their attractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getRuntime
    -0.38
     GenerationType
    -0.37
     senderismo
    -0.35
     boxeo
    -0.35
    Personendaten
    -0.35
    BoxShadow
    -0.34
    ittoria
    -0.34
     fichiers
    -0.32
     démocratique
    -0.31
     pán
    -0.31
    POSITIVE LOGITS
     rides
    1.33
     ride
    1.17
     attractions
    1.14
     attraction
    1.09
     amusement
    1.08
     Rides
    1.02
     theme
    0.95
     Attraction
    0.92
    attraction
    0.92
    rides
    0.91
    Activations Density 0.179%

    No Known Activations