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. 21-GEMMASCOPE-RES-16K
    6. 6624
    Prev
    Next
    INDEX
    Explanations

    phrases and contexts related to home life and family responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.64
     &___
    -0.63
    AddTagHelper
    -0.61
     förr
    -0.56
    ImageContext
    -0.56
    DrawerToggle
    -0.56
     hObject
    -0.54
     pè
    -0.53
    tvguidetime
    -0.53
    ⓧ
    -0.52
    POSITIVE LOGITS
     stay
    1.60
    stay
    1.51
     Stay
    1.48
     staying
    1.46
     stayed
    1.43
    Stay
    1.42
     STAY
    1.31
     stays
    1.29
    STAY
    1.28
    Staying
    1.27
    Activations Density 0.190%

    No Known Activations