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

    Neuronpedia

    Jacobian LensNEW
    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. 15-GEMMASCOPE-RES-16K
    11. 10452
    Prev
    Next
    INDEX
    Explanations

    elements related to community support and outreach initiatives

    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
     виправивши
    -1.01
    +#+#
    -0.91
    RectangleBorder
    -0.87
    PerformLayout
    -0.83
    IntoConstraints
    -0.80
     дописавши
    -0.76
     kaynağından
    -0.71
     ProtoMessage
    -0.70
     StringTokenizer
    -0.70
    ContentAsync
    -0.69
    POSITIVE LOGITS
     high
    0.58
     primarily
    0.52
     provides
    0.51
     eight
    0.49
     six
    0.47
     seven
    0.46
    JFrame
    0.45
    high
    0.45
    主に
    0.45
     offers
    0.44
    Activations Density 0.463%

    No Known Activations