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. 16-GEMMASCOPE-RES-16K
    6. 12239
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships, particularly those involving grandmothers and grandchildren

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

    Family relationships (grandparents, grandson, uncle)

    np_acts-logits-general · gemini-2.0-flash

    grandfamily members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.79
    angliski
    -0.79
    Akt
    -0.72
    DataMember
    -0.72
    hakti
    -0.71
     Hati
    -0.71
     SafeMath
    -0.70
    enumi
    -0.70
    ंदीखरीदारी
    -0.68
     communiquez
    -0.66
    POSITIVE LOGITS
    Grandpa
    0.92
     grandparents
    0.91
     Grandpa
    0.90
     GRAND
    0.84
    Grandma
    0.83
     Grandfather
    0.82
     grandpa
    0.82
     grandfather
    0.81
     grandma
    0.81
    Grand
    0.79
    Activations Density 0.089%

    No Known Activations