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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 169
    Prev
    Next
    INDEX
    Explanations

    variations of the name "Ber" in different contexts

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

    references to specific names, particularly related to a person's name or title

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

    words beginning with ber

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     AssemblyCulture
    -0.66
    Cyfeiriadau
    -0.64
     typelib
    -0.62
    Abit
    -0.61
    ValueStyle
    -0.61
    ImageContext
    -0.60
    masalah
    -0.58
    fao
    -0.57
     istore
    -0.55
    kepada
    -0.55
    POSITIVE LOGITS
    Ber
    0.88
     Ber
    0.81
     BER
    0.64
     Beren
    0.61
     Berk
    0.58
    ber
    0.58
     beret
    0.57
     ber
    0.55
     كومونز
    0.54
    ंदीखरीदारी
    0.54
    Activations Density 0.019%

    No Known Activations