© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10690
    Prev
    Next
    INDEX
    Explanations

    references to chess tournaments and notable players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    defeating someone in a competition

    np_acts-logits-general · gemini-2.0-flash

    defending champions, former winners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 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
    DOCTYPE
    -0.61
    jsonwebtoken
    -0.52
     cle
    -0.52
    kort
    -0.48
    FormState
    -0.47
    PreInfinity
    -0.46
    uerre
    -0.45
    doctype
    -0.44
    handleClose
    -0.43
    CSharp
    -0.43
    POSITIVE LOGITS
     defending
    1.38
     reigning
    1.11
     defend
    0.89
     defends
    0.85
    reign
    0.82
    Reign
    0.81
    Def
    0.79
    rungsseite
    0.75
     defended
    0.75
     Def
    0.74
    Activations Density 0.104%

    No Known Activations