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. 20-GEMMASCOPE-RES-16K
    6. 8002
    Prev
    Next
    INDEX
    Explanations

    references to biological research and experimental methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    birds, especially laying hens

    np_acts-logits-general · gemini-2.0-flash

    laying hens and poultry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     harap
    -0.59
    Fiona
    -0.59
     Lyons
    -0.58
     leone
    -0.55
    ंदीखरीदारी
    -0.54
     Fiona
    -0.53
     werewolf
    -0.53
    balleur
    -0.52
     toothpaste
    -0.52
     dente
    -0.52
    POSITIVE LOGITS
     bird
    1.81
     birds
    1.72
     Bird
    1.56
     avian
    1.53
     feathers
    1.51
    Bird
    1.50
     Birds
    1.49
    bird
    1.46
    Birds
    1.40
     BIRD
    1.39
    Activations Density 0.303%

    No Known Activations