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. 5-GEMMASCOPE-RES-16K
    6. 1859
    Prev
    Next
    INDEX
    Explanations

    references to children and child-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.84
    CreateMap
    -0.66
    hängt
    -0.66
    yelitis
    -0.66
     tudo
    -0.66
    яза
    -0.65
     Sess
    -0.65
     كومونز
    -0.63
    ็จ
    -0.63
     Mante
    -0.63
    POSITIVE LOGITS
     children
    2.30
    children
    2.05
     Children
    2.04
    Children
    2.02
     CHILDREN
    1.79
    CHILDREN
    1.74
     childrens
    1.55
    childrens
    1.47
     kids
    1.47
     child
    1.42
    Activations Density 0.079%

    No Known Activations