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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 13708
    Prev
    Next
    INDEX
    Explanations

    key terms related to scientific data analysis and its application in healthcare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnsafeEnabled
    -0.77
     ProtoMessage
    -0.67
    URLException
    -0.66
    LookAnd
    -0.65
    AccessorTable
    -0.61
     resourceCulture
    -0.61
    stateMutability
    -0.57
     defaultstate
    -0.55
    Personensuche
    -0.55
    djangoproject
    -0.55
    POSITIVE LOGITS
     decision
    1.23
     decisions
    1.17
     planning
    1.13
    decision
    1.08
     deciding
    1.06
     decide
    1.03
     Decision
    0.99
     Decisions
    0.99
    Decision
    0.95
     Planning
    0.95
    Activations Density 0.619%

    No Known Activations