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. 7-GEMMASCOPE-RES-16K
    6. 8959
    Prev
    Next
    INDEX
    Explanations

    concepts related to the state of being alive or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Puritans
    -0.93
     дописавши
    -0.93
    IUrlHelper
    -0.90
    InSection
    -0.86
     Northam
    -0.85
     skunk
    -0.84
     esboço
    -0.82
    ConstraintMaker
    -0.81
    Istorija
    -0.81
    PHeader
    -0.81
    POSITIVE LOGITS
     living
    1.82
     Living
    1.65
    Living
    1.59
     lived
    1.53
     LIVING
    1.50
     live
    1.50
    living
    1.49
    LIVING
    1.37
     Live
    1.37
    Live
    1.33
    Activations Density 0.059%

    No Known Activations