© 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. 30-GEMMASCOPE-RES-16K
    11. 10932
    Prev
    Next
    INDEX
    Explanations

    connections and attachments between objects or components

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

    meaning "joined" or "affixed"

    np_acts-logits-general · gemini-2.0-flash

    connected to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gallimard
    -0.43
     noDo
    -0.43
     Hintergrund
    -0.39
    úgó
    -0.38
    richTextPanel
    -0.38
    Kariera
    -0.38
    matchCondition
    -0.38
    #
    -0.37
    úrate
    -0.37
     Bewußt
    -0.37
    POSITIVE LOGITS
     connected
    1.41
     connect
    1.33
     attached
    1.30
     attach
    1.20
    connected
    1.20
     connecting
    1.19
     Connected
    1.18
     connects
    1.18
    connect
    1.16
    Connected
    1.16
    Activations Density 0.585%

    No Known Activations