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. 6650
    Prev
    Next
    INDEX
    Explanations

    elements related to items on a shopping list, particularly newborn-specific products

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

    babies and diapers

    np_acts-logits-general · gemini-2.0-flash

    baby diapers and covers

    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-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
    GraphicsUnit
    -0.65
     Schülern
    -0.63
    Students
    -0.54
     pupils
    -0.52
    BeginContext
    -0.51
     Students
    -0.51
     Schüler
    -0.51
     elever
    -0.51
     Pupils
    -0.50
     Schülerinnen
    -0.49
    POSITIVE LOGITS
     baby
    1.69
     Baby
    1.51
    baby
    1.50
    Baby
    1.44
     infant
    1.40
     babies
    1.39
     BABY
    1.34
     Babies
    1.31
    BABY
    1.31
    Babies
    1.26
    Activations Density 0.239%

    No Known Activations