Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 9193
    Prev
    Next
    INDEX
    Explanations

    specific items and components, particularly related to household tools and cooking items

    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
    UnsafeEnabled
    -0.82
     disponibilités
    -0.72
    @[+][
    -0.69
     typelib
    -0.67
    IntoConstraints
    -0.65
     الدولى
    -0.65
     ErrIntOverflow
    -0.65
     Audiodateien
    -0.64
     Sinks
    -0.63
     plufieurs
    -0.63
    POSITIVE LOGITS
     kit
    0.58
     tab
    0.54
     proof
    0.50
     tabs
    0.49
    quard
    0.48
     separator
    0.48
     insert
    0.48
     bar
    0.47
     Cote
    0.47
    -/
    0.47
    Activations Density 0.562%

    No Known Activations