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. 13988
    Prev
    Next
    INDEX
    Explanations

    statements that assert the existence or relevance of a specific fact

    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
     we
    -1.18
     they
    -1.16
     he
    -1.12
     it
    -0.96
     I
    -0.92
     
    -0.90
     you
    -0.89
     a
    -0.83
     the
    -0.83
     she
    -0.79
    POSITIVE LOGITS
     CreateTagHelper
    1.88
     المعيارى
    1.48
    MLLoader
    1.42
    tagHelperRunner
    1.42
    RenderAtEndOf
    1.41
    ########.
    1.40
    AndEndTag
    1.36
     تضيفلها
    1.36
     ―――――
    1.36
    IUrlHelper
    1.35
    Activations Density 0.421%

    No Known Activations