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. 6610
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational structures and responsibilities

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

    preceding names of departments

    np_acts-logits-general · gemini-2.0-flash

    department and its staff

    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
    WebServlet
    -0.61
    Parcelize
    -0.59
    awtextra
    -0.58
    PreferredItem
    -0.58
     judiciales
    -0.57
    日閲覧
    -0.57
    ]='\
    -0.55
    FunctionFlags
    -0.55
    #![
    -0.53
    yarnpkg
    -0.53
    POSITIVE LOGITS
     department
    2.22
     departments
    1.76
    department
    1.71
     dept
    1.69
     Department
    1.58
     division
    1.53
     Dept
    1.48
     DEPARTMENT
    1.44
    Department
    1.39
     departamento
    1.37
    Activations Density 0.290%

    No Known Activations