© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 2721
    Prev
    Next
    INDEX
    Explanations

    words related to significant size or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.53
    antMatchers
    -0.50
    cella
    -0.49
    rensen
    -0.49
    èdia
    -0.48
    FindBy
    -0.48
     harass
    -0.45
     stanov
    -0.43
    tır
    -0.43
    几种
    -0.43
    POSITIVE LOGITS
     huge
    2.12
     gigantic
    2.05
    Huge
    2.00
     HUGE
    1.97
     Huge
    1.97
     giant
    1.95
    huge
    1.94
     big
    1.92
     enormous
    1.84
     large
    1.81
    Activations Density 0.402%

    No Known Activations