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. 10-GEMMASCOPE-RES-16K
    6. 11731
    Prev
    Next
    INDEX
    Explanations

    elements and descriptions of living spaces and their conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eventually
    -0.43
     stand
    -0.37
     lift
    -0.36
     nak
    -0.36
    volume
    -0.36
     ultimately
    -0.35
     volume
    -0.35
    Koordinaten
    -0.35
     pik
    -0.35
     Eventually
    -0.35
    POSITIVE LOGITS
     rooms
    0.70
    Rooms
    0.68
     bedrooms
    0.67
    хьтан
    0.66
     säll
    0.66
     Rooms
    0.65
     room
    0.62
     bedroom
    0.62
     Room
    0.61
    FormTagHelper
    0.60
    Activations Density 0.136%

    No Known Activations