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. 5571
    Prev
    Next
    INDEX
    Explanations

    elements of code structure, particularly relating to method definitions and braces

    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
     himo
    -0.48
     automata
    -0.47
    bellar
    -0.45
     kask
    -0.44
     Droid
    -0.42
     bulunur
    -0.41
    ApiModel
    -0.40
     trụ
    -0.40
     نسخة
    -0.39
     Sphere
    -0.39
    POSITIVE LOGITS
    ScopeManager
    0.84
    awtextra
    0.81
     Roskov
    0.74
    uxxxx
    0.72
    +#+#
    0.71
    ViewImports
    0.70
    enderror
    0.69
     initComponents
    0.69
    addContainerGap
    0.67
    WebControls
    0.65
    Activations Density 0.024%

    No Known Activations