© 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. 5-GEMMASCOPE-RES-16K
    6. 5177
    Prev
    Next
    INDEX
    Explanations

    references to photography and taking pictures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     connais
    -0.61
    DispatchToProps
    -0.59
    gnore
    -0.57
     Wiktionnaire
    -0.56
    itemName
    -0.54
     menuItem
    -0.54
    ضان
    -0.53
     channel
    -0.52
    srand
    -0.52
     évek
    -0.50
    POSITIVE LOGITS
     photographs
    1.77
     photos
    1.77
     photograph
    1.65
     photo
    1.58
     pictures
    1.57
     images
    1.48
     Photographs
    1.45
     foto
    1.43
    Photographs
    1.41
     pics
    1.41
    Activations Density 0.232%

    No Known Activations