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. 11-GEMMASCOPE-RES-16K
    6. 5488
    Prev
    Next
    INDEX
    Explanations

    code structures, particularly switch-case statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pikir
    -0.42
    inian
    -0.42
     detik
    -0.42
    oudou
    -0.41
    getContentPane
    -0.41
    ждународ
    -0.40
     Nut
    -0.40
    емов
    -0.40
    ILIA
    -0.40
    werker
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    0.88
    ConstraintMaker
    0.87
    awtextra
    0.81
    IBOutlet
    0.80
    \}\\
    0.78
    stateProvider
    0.78
    IntoConstraints
    0.78
     تضيفلها
    0.76
     typelib
    0.75
    AddTagHelper
    0.74
    Activations Density 0.050%

    No Known Activations