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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 63221
    Prev
    Next
    INDEX
    Explanations

    references to fur and its qualities

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

    fur, fur quality, fur color

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Wiktionnaire
    -0.54
    readystatechange
    -0.53
    awtextra
    -0.51
    plak
    -0.51
    MemoryWarning
    -0.51
    KommentareTeilen
    -0.50
    denk
    -0.50
    Reese
    -0.50
    uvwxyz
    -0.49
    DataAnnotations
    -0.49
    POSITIVE LOGITS
     Fu
    0.87
     Fur
    0.87
     FUR
    0.84
     fur
    0.82
     fu
    0.80
    Fur
    0.77
    fu
    0.75
    Fu
    0.73
     Furman
    0.69
    fur
    0.69
    Activations Density 0.009%

    No Known Activations