© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 11617
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to visual details and characteristics of people or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.63
     lenker
    -0.61
     Roskov
    -0.59
    SuccessListener
    -0.58
     المعيارى
    -0.55
     favoritas
    -0.55
     gradova
    -0.54
     exemplu
    -0.53
     démocratie
    -0.53
    apunov
    -0.53
    POSITIVE LOGITS
     figure
    1.13
     figures
    1.00
     familiar
    0.99
     tall
    0.94
     unfamiliar
    0.94
     strange
    0.88
    figure
    0.87
     Figure
    0.86
     voice
    0.84
    familiar
    0.84
    Activations Density 0.271%

    No Known Activations