Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 5034
    Prev
    Next
    INDEX
    Explanations

    special characters and mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PSV
    -0.46
    Collegamenti
    -0.46
     !=
    -0.43
    PCs
    -0.42
    INTRODUCTION
    -0.42
    viewers
    -0.41
     ellas
    -0.40
    Agu
    -0.40
    CWE
    -0.40
    refu
    -0.39
    POSITIVE LOGITS
    mybatisplus
    0.97
     ")");
    0.78
    ScopeManager
    0.70
    UnusedPrivate
    0.70
     estekak
    0.70
     unknownFields
    0.69
    NameInMap
    0.69
     nakalista
    0.69
     '\\;'
    0.69
    )");
    
    0.68
    Activations Density 0.494%

    No Known Activations