Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11068
    Prev
    Next
    INDEX
    Explanations

    elements of football game analysis

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

    "Chelsea" or mentions of "Chelsea"

    np_acts-logits-general · gemini-2.0-flash

    Chelsea and Blues

    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
     aer
    -0.56
     Volu
    -0.52
     Pollo
    -0.51
     Dund
    -0.50
     Idris
    -0.50
    LinkId
    -0.49
     Nik
    -0.49
    plist
    -0.49
     reconcili
    -0.49
     Registers
    -0.49
    POSITIVE LOGITS
     Chelsea
    1.21
    Chelsea
    1.02
     chelsea
    0.90
    chelsea
    0.86
     Blues
    0.74
     Stamford
    0.71
    chel
    0.67
    prefixer
    0.67
    CFC
    0.64
    Blues
    0.64
    Activations Density 0.150%

    No Known Activations