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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9183
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships, particularly highlighting the role of fathers and mothers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    ագրություններ
    -0.80
     שוליים
    -0.63
     ModelExpression
    -0.62
    NameInMap
    -0.58
     विश्वसनीयता
    -0.58
     للمعارف
    -0.56
     CreateTagHelper
    -0.54
     distanciation
    -0.54
    vermögen
    -0.53
     nonUne
    -0.53
    POSITIVE LOGITS
     dad
    1.12
     papa
    1.11
     Dad
    1.11
     daddy
    1.09
    Dad
    1.06
     mother
    1.05
     father
    1.05
     mom
    1.03
     mommy
    1.01
     Father
    1.01
    Activations Density 0.110%

    No Known Activations