© 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. 1574
    Prev
    Next
    INDEX
    Explanations

    entities related to governmental and organizational structures

    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
    parsedMessage
    -0.71
    ArgumentParser
    -0.63
     defaultstate
    -0.59
    WithIOException
    -0.57
     للمعارف
    -0.53
    AccessorTable
    -0.52
    SourceChecksum
    -0.51
     Infórmanos
    -0.51
    EditorBrowsable
    -0.50
     становника
    -0.49
    POSITIVE LOGITS
     chief
    0.46
    ✭✭
    0.43
     Chief
    0.41
    osexuality
    0.36
     senator
    0.36
     PCP
    0.35
     scheduler
    0.34
    utriche
    0.34
     بخوانید
    0.33
     COO
    0.33
    Activations Density 0.259%

    No Known Activations