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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12354
    Prev
    Next
    INDEX
    Explanations

    references to structured data formats or content types involving forms and articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageOf
    -0.90
    tagHelperRunner
    -0.79
    ValueStyle
    -0.79
    IUrlHelper
    -0.76
     NSCoder
    -0.76
    IsMutable
    -0.73
     ProtoMessage
    -0.73
    SharedDtor
    -0.73
    PostInfinity
    -0.73
     propOrder
    -0.73
    POSITIVE LOGITS
     directly
    0.33
     directement
    0.31
     daire
    0.31
     Directly
    0.30
     part
    0.30
     Direct
    0.29
     tehd
    0.28
     where
    0.28
    Direct
    0.28
     and
    0.27
    Activations Density 0.099%

    No Known Activations