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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3388
    Prev
    Next
    INDEX
    Explanations

    References to individuals' roles in sports, particularly in football management

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

    Sports teams or leagues

    np_acts-logits-general · gemini-2.0-flash

    junior/senior ranks

    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
    MigrationBuilder
    -0.72
     vowel
    -0.55
     nahilalakip
    -0.53
     ExecuteAsync
    -0.52
    +#+#
    -0.52
    DockStyle
    -0.51
    decorate
    -0.50
    Rujuakan
    -0.49
    gettime
    -0.49
     pectin
    -0.49
    POSITIVE LOGITS
     junior
    1.00
     juniors
    0.95
     senior
    0.90
    junior
    0.86
     Junior
    0.83
    senior
    0.81
     Senior
    0.77
    Junior
    0.76
     seniors
    0.76
     Juniors
    0.75
    Activations Density 0.178%

    No Known Activations