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. 7647
    Prev
    Next
    INDEX
    Explanations

    terms related to roles and relationships in partnerships and affiliations

    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
     Мексичка
    -1.01
    ValueStyle
    -0.92
    ResumeLayout
    -0.82
     Normdatei
    -0.82
    IntoConstraints
    -0.82
    Autoritní
    -0.80
    extAlignment
    -0.79
     SafeMath
    -0.79
    IVEREF
    -0.78
    MigrationBuilder
    -0.77
    POSITIVE LOGITS
    chaft
    0.53
     list
    0.53
     utama
    0.52
     directos
    0.52
    となる
    0.49
     thereof
    0.49
     circonstances
    0.49
     immédi
    0.47
    いない
    0.46
     masculinos
    0.46
    Activations Density 0.686%

    No Known Activations