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. 15-GEMMASCOPE-RES-16K
    6. 2428
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and their context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    djangoproject
    -0.62
     الرخصة
    -0.57
     CreateTagHelper
    -0.54
    らせる
    -0.50
    ceda
    -0.50
     crossorigin
    -0.49
     مرئيه
    -0.49
    PLS
    -0.49
    락
    -0.49
    zusetzen
    -0.49
    POSITIVE LOGITS
    Slf
    0.69
     but
    0.65
    նակ
    0.64
    principalTable
    0.62
     and
    0.62
    EndProject
    0.56
    XtraEditors
    0.54
    曖昧さ回避
    0.54
    but
    0.52
     правда
    0.52
    Activations Density 0.255%

    No Known Activations