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. 13640
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to disciplinary actions

    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
     ExecuteAsync
    -0.73
    aryen
    -0.68
    ValueStyle
    -0.64
    مصادر
    -0.58
     CreateTagHelper
    -0.54
     Audiodateien
    -0.54
     المعيارى
    -0.54
     ویکی‌پدیای
    -0.54
     Obrador
    -0.54
    msgTypes
    -0.53
    POSITIVE LOGITS
     license
    1.27
     licensing
    1.18
     lic
    1.16
     License
    1.11
     licensed
    1.10
     licenses
    1.08
    License
    1.08
     Lic
    1.07
     profession
    1.07
     Professional
    1.07
    Activations Density 0.367%

    No Known Activations