© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 439
    Prev
    Next
    INDEX
    Explanations

    references related to photography sessions and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    taking or creating images

    np_acts-logits-general · gemini-2.0-flash

    photograph, picture, portrait

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '),
    -0.35
    TextWatcher
    -0.33
     rénovation
    -0.32
    Jegyzetek
    -0.31
     arquitetura
    -0.31
     nocy
    -0.30
    AnimationsModule
    -0.30
     Transporte
    -0.30
     verfolgen
    -0.30
    organizzazione
    -0.30
    POSITIVE LOGITS
     photoshoot
    1.16
     photographed
    1.02
     photographer
    1.02
     photograph
    0.98
     photographers
    0.96
     photographing
    0.94
    Photograph
    0.93
     photography
    0.92
    photograph
    0.92
     Photographer
    0.91
    Activations Density 0.132%

    No Known Activations