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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-GEMMASCOPE-RES-16K
    6. 14750
    Prev
    Next
    INDEX
    Explanations

    references to mathematical and algebraic structures or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <>",
    -0.90
    ThroughAttribute
    -0.88
    OGND
    -0.80
    webElement
    -0.78
     Roskov
    -0.77
    PerformLayout
    -0.76
    IUrlHelper
    -0.75
     SqlParameter
    -0.75
    QMetaType
    -0.73
    aarrggbb
    -0.71
    POSITIVE LOGITS
     The
    0.65
    “
    0.62
     “
    0.58
     "
    0.56
    The
    0.52
     '
    0.49
    ような
    0.48
    newblock
    0.48
    "
    0.48
     Phry
    0.48
    Activations Density 0.631%

    No Known Activations