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. 5-GEMMASCOPE-RES-16K
    6. 4545
    Prev
    Next
    INDEX
    Explanations

    references to rectangle or GUI-related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endpush
    -1.12
    migrationBuilder
    -0.88
     onCancelled
    -0.80
    -------------</
    -0.77
     casó
    -0.76
    QMetaType
    -0.69
    évaluateur
    -0.69
    گزاری
    -0.68
    viewDidLoad
    -0.65
    TargetException
    -0.65
    POSITIVE LOGITS
    Rect
    2.07
     rect
    1.98
     Rect
    1.91
    rect
    1.89
     rectangle
    1.61
     RECT
    1.49
     Rectangle
    1.48
    RECT
    1.41
     rectangles
    1.40
    Rectangle
    1.36
    Activations Density 0.086%

    No Known Activations