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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10121
    Prev
    Next
    INDEX
    Explanations

    references to football clubs and players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intime
    -0.45
     windshield
    -0.44
     sternum
    -0.43
    ิ้น
    -0.42
    tréal
    -0.42
     husband
    -0.41
    Empire
    -0.41
     elett
    -0.41
    SuppressLint
    -0.40
     sumpay
    -0.40
    POSITIVE LOGITS
     youth
    1.16
     junior
    1.11
     Youth
    1.04
    junior
    1.00
     juniors
    0.99
    youth
    0.98
    Youth
    0.95
     Junior
    0.94
     juvenil
    0.89
    Junior
    0.88
    Activations Density 0.151%

    No Known Activations