© 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-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8049
    Prev
    Next
    INDEX
    Explanations

    references to various species of animals, particularly birds and amphibians

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yüzden
    -0.33
     paces
    -0.32
    뀜
    -0.31
     Glanz
    -0.30
    dden
    -0.30
     nötig
    -0.29
    ˚
    -0.28
     Fres
    -0.28
    ureusement
    -0.28
     TLC
    -0.28
    POSITIVE LOGITS
     lizard
    1.70
     turtle
    1.70
     elephant
    1.66
     crocodile
    1.66
     squirrel
    1.64
     frog
    1.63
     bird
    1.62
     alligator
    1.62
     owl
    1.60
     rabbit
    1.58
    Activations Density 0.552%

    No Known Activations