© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13624
    Prev
    Next
    INDEX
    Explanations

    specific statistics and performance metrics related to sports events

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

    Sports teams or players

    np_acts-logits-general · gemini-2.0-flash

    failure and loss

    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
     sophistic
    -0.56
     flourishing
    -0.50
    xtext
    -0.49
    APPLAUSE
    -0.49
     thriving
    -0.49
    SUCCESS
    -0.48
     erfolgreich
    -0.48
     enhanced
    -0.47
    ędziesz
    -0.47
    Demand
    -0.47
    POSITIVE LOGITS
     failed
    0.98
     failing
    0.98
     losing
    0.97
     inability
    0.94
     poor
    0.91
     lost
    0.89
     conceding
    0.87
     lack
    0.86
     fail
    0.86
     fails
    0.85
    Activations Density 0.222%

    No Known Activations