© 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. 28-GEMMASCOPE-RES-16K
    11. 7989
    Prev
    Next
    INDEX
    Explanations

    references to relationships and dependencies among concepts or elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "to do with"

    np_acts-logits-general · gemini-2.0-flash

    related to or have to do with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    colhead
    -0.38
     Vier
    -0.35
    CrossRef
    -0.34
     auteurs
    -0.33
    Debugger
    -0.33
     val
    -0.32
     auteur
    -0.32
    kannt
    -0.32
     useAppContext
    -0.32
     губ
    -0.31
    POSITIVE LOGITS
     related
    1.58
     relating
    1.41
    related
    1.36
     relates
    1.33
     Related
    1.32
     relacionado
    1.27
     relate
    1.23
     związane
    1.19
     RELATED
    1.18
     riguard
    1.18
    Activations Density 0.613%

    No Known Activations