© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 10825
    Prev
    Next
    INDEX
    Explanations

    phrases related to photography and images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    horabuena
    -0.56
    createStatement
    -0.55
     cantit
    -0.51
    seamnă
    -0.49
    bitat
    -0.48
    леге
    -0.47
     Wiktionnaire
    -0.47
     trilha
    -0.47
    getDoctrine
    -0.46
     školy
    -0.46
    POSITIVE LOGITS
     images
    1.20
     pictures
    1.14
     photograph
    1.11
     image
    1.10
     Images
    1.07
     photographs
    1.06
     picture
    1.03
     photos
    1.03
     Pictures
    0.97
     depicting
    0.94
    Activations Density 0.270%

    No Known Activations