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. 3-GEMMASCOPE-RES-16K
    6. 8544
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their amino acid-related components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     au
    -0.51
     Real
    -0.49
     Boeh
    -0.48
     VEHICLE
    -0.48
     regulated
    -0.47
    extérieur
    -0.47
     Руси
    -0.47
    arsa
    -0.47
    ghold
    -0.47
    homa
    -0.47
    POSITIVE LOGITS
     amin
    2.22
     amino
    2.05
    Amino
    2.00
     Amino
    1.99
    amino
    1.98
    Amin
    1.90
     Amin
    1.79
    amin
    1.74
    amine
    1.28
    PerformLayout
    1.22
    Activations Density 0.376%

    No Known Activations