© 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. 5-GEMMASCOPE-RES-16K
    6. 5034
    Prev
    Next
    INDEX
    Explanations

    mentions of specific days and the significance of those days in various contexts

    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
     nonatomic
    -0.62
     McCon
    -0.59
    displayquote
    -0.58
     XCTest
    -0.57
    WebElementEntity
    -0.57
     Raceway
    -0.54
    Intu
    -0.54
    VersionUID
    -0.53
    adona
    -0.52
    ღ
    -0.51
    POSITIVE LOGITS
    第一天
    0.80
    ValueStyle
    0.72
    rungsseite
    0.67
    initComponents
    0.58
     fubject
    0.56
    Sucesor
    0.56
    EndProject
    0.55
     Anfang
    0.55
     시작
    0.55
    enterOuterAlt
    0.55
    Activations Density 0.184%

    No Known Activations