Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 10093
    Prev
    Next
    INDEX
    Explanations

    references to events involving actors and their experiences in the entertainment industry

    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
    prilis
    -0.52
    ("/:
    -0.52
    ("/{
    -0.52
    ('/:
    -0.50
    ValueStyle
    -0.48
     anymore
    -0.45
     notizie
    -0.45
     dále
    -0.44
    BorderFactory
    -0.44
    jelent
    -0.43
    POSITIVE LOGITS
     nearly
    2.56
    nearly
    2.44
     almost
    2.32
     Nearly
    2.26
    almost
    2.23
    Nearly
    2.17
     Almost
    2.14
    Almost
    2.11
     quase
    2.01
     beinahe
    1.92
    Activations Density 0.331%

    No Known Activations