© 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. 21-GEMMASCOPE-RES-16K
    6. 8222
    Prev
    Next
    INDEX
    Explanations

    references to government ministries and their respective functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.78
    enumi
    -0.72
    parsedMessage
    -0.67
    脚注の使い方
    -0.63
    tagHelperRunner
    -0.61
    TestingModule
    -0.61
    BeginContext
    -0.59
    Secretary
    -0.57
    SequentialGroup
    -0.57
     SECRETARY
    -0.56
    POSITIVE LOGITS
     culture
    0.66
     Education
    0.61
     education
    0.61
     finance
    0.61
     Finance
    0.60
     defense
    0.59
    education
    0.55
     Health
    0.55
    Education
    0.55
     Culture
    0.55
    Activations Density 0.096%

    No Known Activations