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. 0-GEMMASCOPE-RES-16K
    6. 274
    Prev
    Next
    INDEX
    Explanations

    boolean data type references and keywords in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -1.01
    ंदीखरीदारी
    -0.85
    Datuak
    -0.82
    PerformLayout
    -0.81
     Audiodateien
    -0.77
    copyWith
    -0.77
     الحره
    -0.75
    ItemBackground
    -0.75
    icoot
    -0.74
    SBATCH
    -0.74
    POSITIVE LOGITS
    Bool
    0.96
    Boolean
    0.89
    boolean
    0.85
     holes
    0.81
     gaps
    0.80
     boolean
    0.80
    bool
    0.74
     bool
    0.69
     Boolean
    0.65
     BOOLEAN
    0.65
    Activations Density 0.111%

    No Known Activations