© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 2521
    Prev
    Next
    INDEX
    Explanations

    elements related to photography, particularly capturing images and photographic techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.70
    LayoutPanel
    -0.67
    internalType
    -0.67
     ControllerBase
    -0.67
    GraphicsUnit
    -0.66
    estacks
    -0.63
     TestBed
    -0.62
    cellation
    -0.59
    conio
    -0.58
    WebServlet
    -0.58
    POSITIVE LOGITS
     photographers
    1.36
     photographer
    1.35
     photography
    1.31
     camera
    1.24
     Photography
    1.21
     photo
    1.16
     photographic
    1.15
     photographing
    1.15
     Photographer
    1.12
     photos
    1.10
    Activations Density 0.474%

    No Known Activations