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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15607
    Prev
    Next
    INDEX
    Explanations

    content related to trails and outdoor activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cities
    -0.37
     citizens
    -0.35
     ciudad
    -0.35
     vitaminas
    -0.34
     religieuses
    -0.34
     blé
    -0.32
     beneficiary
    -0.32
    Océ
    -0.32
     city
    -0.31
     milliard
    -0.31
    POSITIVE LOGITS
     hike
    0.90
     hiked
    0.85
     hiking
    0.79
     hikers
    0.79
     hiker
    0.77
     hikes
    0.75
     climb
    0.72
     Hike
    0.72
    hike
    0.72
     Hiking
    0.69
    Activations Density 0.252%

    No Known Activations