© 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. 22-GEMMASCOPE-RES-16K
    6. 5469
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and encouragement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ➩
    -0.41
    RemoveField
    -0.39
    GMENT
    -0.37
    Hochspringen
    -0.37
    setViewportView
    -0.34
    Portály
    -0.34
    NegativeButton
    -0.34
    蚪
    -0.34
    PreInfinity
    -0.34
     seguido
    -0.34
    POSITIVE LOGITS
    RefNanny
    0.53
    ResumeLayout
    0.50
     ape
    0.49
    RTSC
    0.46
    Numerade
    0.46
     pseud
    0.44
     XCTest
    0.43
     Pseud
    0.43
    Calend
    0.42
     esc
    0.42
    Activations Density 0.166%

    No Known Activations