© 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. 25-GEMMASCOPE-RES-16K
    6. 81
    Prev
    Next
    INDEX
    Explanations

    words related to photography and individual photographers' accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 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
     Camera
    -0.68
     camera
    -0.64
    Cam
    -0.64
     Cam
    -0.63
    PageRoute
    -0.63
     CAM
    -0.61
     AssemblyCompany
    -0.61
     cameras
    -0.60
     fotográfica
    -0.59
     Cameras
    -0.59
    POSITIVE LOGITS
     portraits
    0.79
     portrait
    0.73
     candid
    0.69
     session
    0.68
     editorial
    0.68
     posed
    0.68
     cand
    0.67
     lifestyle
    0.66
    Lifestyle
    0.64
     Lifestyle
    0.64
    Activations Density 0.257%

    No Known Activations