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. 10661
    Prev
    Next
    INDEX
    Explanations

    terms related to legal requirements and obligations

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

    Tokens preceding "require/required/requirements"

    np_acts-logits-general · gemini-2.0-flash

    requirement

    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
    enumi
    -0.82
     Spisak
    -0.76
    Jeografia
    -0.74
    enumii
    -0.74
    pausal
    -0.72
    principalColumn
    -0.70
    MessageTagHelper
    -0.68
    Tembelea
    -0.67
    Xna
    -0.67
    下载附件
    -0.66
    POSITIVE LOGITS
    resave
    0.58
    sas
    0.53
    PhysRev
    0.51
     spécial
    0.48
     catég
    0.48
    lyte
    0.48
    nuovo
    0.47
     REQ
    0.47
    íř
    0.47
    DataAnnotations
    0.46
    Activations Density 0.126%

    No Known Activations