© 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. 6810
    Prev
    Next
    INDEX
    Explanations

    sports positions and roles within various athletic contexts

    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
    printStackTrace
    -0.57
    zzar
    -0.52
     poveznice
    -0.49
    pexpr
    -0.49
    makeText
    -0.48
    Portale
    -0.48
    Rptr
    -0.47
     виправивши
    -0.46
    writeFieldEnd
    -0.45
    mpagne
    -0.45
    POSITIVE LOGITS
    sidemargin
    0.44
    providedIn
    0.40
     hopeful
    0.38
     singer
    0.38
    食べたい
    0.35
     aim
    0.35
    bootstrapcdn
    0.35
    kologie
    0.35
     hungry
    0.35
     coach
    0.34
    Activations Density 0.142%

    No Known Activations