© 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. 22-GEMMASCOPE-RES-16K
    11. 6273
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to programming or software documentation

    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
    führende
    -0.42
     AssemblyCulture
    -0.42
    RectangleBorder
    -0.38
     NSCoder
    -0.36
    füh
    -0.36
    stateProvider
    -0.35
    الحياه
    -0.35
    BagConstraints
    -0.34
     جای
    -0.33
    rungsseite
    -0.33
    POSITIVE LOGITS
    Παραπομπές
    0.55
     WaitForSeconds
    0.49
    awaiter
    0.46
    Teraz
    0.46
    berdayakan
    0.45
     duration
    0.45
     minutes
    0.45
    duration
    0.44
    MemoryWarning
    0.44
     erection
    0.43
    Activations Density 0.045%

    No Known Activations