© 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. 14-GEMMASCOPE-RES-16K
    6. 4525
    Prev
    Next
    INDEX
    Explanations

    legal terminology and tense relationships related to contracts and legal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    échange
    -0.45
     differentials
    -0.45
     skulls
    -0.43
    хло
    -0.42
     Cooperation
    -0.42
    assertSame
    -0.42
     coopération
    -0.42
     spion
    -0.42
    互
    -0.41
     consent
    -0.41
    POSITIVE LOGITS
    tvguidetime
    0.85
    spesies
    0.80
    LookAnd
    0.70
    AutoresizingMask
    0.69
     onBind
    0.68
    
    0.68
    CppMethod
    0.66
     تانيه
    0.64
    Izvori
    0.64
     itſelf
    0.63
    Activations Density 0.498%

    No Known Activations