© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 8445
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their contributions or roles in community and societal contexts

    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
    ambién
    -0.57
     Könige
    -0.53
     boneca
    -0.53
     Sünde
    -0.51
     Beweis
    -0.51
     متعلقه
    -0.51
     Griechen
    -0.50
     turística
    -0.49
    verifyException
    -0.49
     kapture
    -0.49
    POSITIVE LOGITS
     Episcopal
    0.58
    
    0.56
     ThemeData
    0.52
     BorderRadius
    0.49
     Lutheran
    0.47
    Epis
    0.46
     Episcop
    0.45
     Anglican
    0.44
     church
    0.43
     Presbyterian
    0.42
    Activations Density 0.186%

    No Known Activations