© 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. 5-GEMMASCOPE-RES-16K
    6. 6448
    Prev
    Next
    INDEX
    Explanations

    specific names and references related to people, places, and medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -1.69
    ER
    -1.28
     Pacer
    -1.06
     Asher
    -0.98
    oler
    -0.97
     Packer
    -0.97
    izer
    -0.97
    ader
    -0.96
    ider
    -0.95
    ger
    -0.94
    POSITIVE LOGITS
    skraft
    0.83
    httphttps
    0.79
     peindre
    0.78
    opsida
    0.78
    Arbitrage
    0.76
    zsef
    0.76
     McNeil
    0.75
    jestic
    0.74
     Corbu
    0.74
    remacy
    0.73
    Activations Density 2.054%

    No Known Activations