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. 10-GEMMASCOPE-RES-16K
    6. 5663
    Prev
    Next
    INDEX
    Explanations

    references to birds and avian species

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CrossRef
    -0.91
    Weblinks
    -0.70
     ActionListener
    -0.68
     maxX
    -0.65
    prepareStatement
    -0.63
     gtx
    -0.63
    cosx
    -0.62
     Expressway
    -0.61
    pośred
    -0.61
     Rued
    -0.60
    POSITIVE LOGITS
     Birds
    1.98
     Bird
    1.96
     bird
    1.94
     birds
    1.91
    Birds
    1.89
    Bird
    1.85
     BIRD
    1.78
     BIRDS
    1.67
    bird
    1.66
    birds
    1.59
    Activations Density 0.429%

    No Known Activations