© 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. 23-GEMMASCOPE-RES-16K
    11. 2306
    Prev
    Next
    INDEX
    Explanations

    specific names, likely related to people or authors in a scholarly context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſmall
    -0.57
    Билгалдахарш
    -0.54
    IContainer
    -0.50
    CheckBreak
    -0.50
    AndroidJUnit
    -0.49
    IsMutable
    -0.48
     AssemblyTitle
    -0.46
     oppress
    -0.46
    Congress
    -0.45
    RetentionPolicy
    -0.45
    POSITIVE LOGITS
    ArgumentParser
    0.37
     betweenstory
    0.36
    SequentialGroup
    0.35
     HFILL
    0.35
     tæ
    0.34
    coffret
    0.31
    awaiter
    0.31
    ->___
    0.30
    MessageOf
    0.30
     uLocal
    0.29
    Activations Density 0.132%

    No Known Activations