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. 13-GEMMASCOPE-RES-16K
    6. 5224
    Prev
    Next
    INDEX
    Explanations

    references to English translations and transcriptions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.65
     فريبيس
    -0.62
     resourceCulture
    -0.60
    setDo
    -0.59
     sauvages
    -0.59
    DockStyle
    -0.57
    WebVitals
    -0.57
     виправивши
    -0.57
    sidemargin
    -0.55
     CreateTagHelper
    -0.54
    POSITIVE LOGITS
    SequentialGroup
    0.65
     siehe
    0.53
    原始内容
    0.51
    詳細は
    0.50
     Arhivirano
    0.49
    bitField
    0.47
    自体は
    0.47
    izacao
    0.46
     details
    0.46
    KOV
    0.46
    Activations Density 0.516%

    No Known Activations