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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15973
    Prev
    Next
    INDEX
    Explanations

    references to cats and their characteristics

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

    cats

    np_acts-logits-general · gemini-2.0-flash

    cat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.51
    cipar
    -0.50
    énario
    -0.49
     يتيمه
    -0.47
    ClientRect
    -0.42
    ')}}">
    -0.41
    msubsup
    -0.40
     nakalista
    -0.40
     Bullock
    -0.40
     paulo
    -0.39
    POSITIVE LOGITS
     cat
    1.34
     cats
    1.27
     feline
    1.22
     Cat
    1.16
     kittens
    1.14
    Cat
    1.11
     Cats
    1.11
     kitten
    1.08
    Cats
    1.05
     kitty
    1.02
    Activations Density 0.067%

    No Known Activations