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. 10852
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or groups

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

    "The" before an organization or location

    np_acts-logits-general · gemini-2.0-flash

    organizations after "the"

    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
    ones
    -0.51
    ia
    -0.43
    od
    -0.42
     correspondiente
    -0.42
    нд
    -0.41
    вающих
    -0.41
    fa
    -0.40
     voulez
    -0.40
     nào
    -0.40
    ONESIA
    -0.40
    POSITIVE LOGITS
     organisation
    1.15
     organization
    1.13
     institución
    0.99
     company
    0.96
     institution
    0.94
    organization
    0.87
     agency
    0.86
    organisation
    0.86
    sidemargin
    0.85
     corporation
    0.81
    Activations Density 0.609%

    No Known Activations