© 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. 3-GEMMASCOPE-RES-16K
    11. 1691
    Prev
    Next
    INDEX
    Explanations

    references to roles, positions, and affiliations within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Key
    -0.42
     Levine
    -0.42
     Ant
    -0.41
     hob
    -0.41
     ant
    -0.40
     !!}
    -0.40
     Vol
    -0.40
     tay
    -0.40
    Key
    -0.39
     Ron
    -0.39
    POSITIVE LOGITS
    IUrlHelper
    0.90
     myſelf
    0.81
    出版年
    0.79
     Theſe
    0.79
    ſelf
    0.77
    ंदीखरीदारी
    0.77
     himſelf
    0.73
    esModule
    0.73
    bootstrapcdn
    0.72
    ValueStyle
    0.72
    Activations Density 0.165%

    No Known Activations