© 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. 20-GEMMASCOPE-RES-16K
    6. 7224
    Prev
    Next
    INDEX
    Explanations

    references to the number of cats and kittens allowed in households

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     utafitiHapana
    -0.49
    بوابة
    -0.48
     Numerade
    -0.45
    Portail
    -0.45
    ValueStyle
    -0.44
     nahilalakip
    -0.44
     CURLOPT
    -0.43
     <<<<<<<<<<<<<<
    -0.43
    complexContent
    -0.42
    ViewChild
    -0.42
    POSITIVE LOGITS
     dogs
    0.59
     veterinarians
    0.57
     mascotas
    0.56
     hewan
    0.55
     vétérina
    0.53
     zvíř
    0.53
     puppies
    0.52
     animals
    0.52
    Dogs
    0.52
     kittens
    0.52
    Activations Density 0.023%

    No Known Activations