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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 1865
    Prev
    Next
    INDEX
    Explanations

    the notion of assurance or confirmation, particularly in contexts related to rest or relaxation

    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
    
    -1.29
     المعرف
    -1.06
     Marlowe
    -1.05
     considérons
    -1.03
    rungsseite
    -1.01
    queryInterface
    -0.98
    tvguidetime
    -0.96
    HasAnnotation
    -0.95
    OGND
    -0.95
     MessageBoxIcon
    -0.93
    POSITIVE LOGITS
     rest
    2.55
     Rest
    2.23
    Rest
    2.23
    rest
    2.15
     REST
    1.84
    REST
    1.73
     rests
    1.52
     rested
    1.37
     resting
    1.35
     resten
    1.25
    Activations Density 0.049%

    No Known Activations