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
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 913
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the concept of a "brand" or "branding."

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

    brand, brands, brand names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tomy
    -0.53
    ucchini
    -0.51
    hio
    -0.49
    AccessFile
    -0.48
    Skocz
    -0.48
    ioterapia
    -0.47
    zysty
    -0.45
     Ditto
    -0.44
    itsi
    -0.44
    eto
    -0.43
    POSITIVE LOGITS
    Brand
    1.07
     Brand
    1.03
     BRAND
    1.02
     brand
    0.99
    brand
    0.93
     Brandt
    0.93
    BRAND
    0.93
    Brands
    0.80
     Brands
    0.79
     Brandon
    0.75
    Activations Density 0.005%

    No Known Activations