© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 14038
    Prev
    Next
    INDEX
    Explanations

    elements related to programming logic, specifically condition statements and value comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kmal
    -0.46
    quale
    -0.46
    ClassNotFound
    -0.44
    Fuzz
    -0.43
    requency
    -0.41
    FORME
    -0.41
    GIUM
    -0.41
     žá
    -0.40
    Give
    -0.39
    LabelTagHelper
    -0.39
    POSITIVE LOGITS
     numberOfRows
    0.77
     insuffisamment
    0.73
     range
    0.72
    aarrggbb
    0.71
    enumii
    0.70
     typelib
    0.68
     ModelExpression
    0.68
    viewDidLoad
    0.68
    PerformLayout
    0.66
    Range
    0.65
    Activations Density 0.707%

    No Known Activations