© 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. 1786
    Prev
    Next
    INDEX
    Explanations

    references to mechanical components or concepts related to machinery

    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
     IndexPath
    -0.69
     RoutedEventArgs
    -0.69
     NSCoder
    -0.64
    FailureListener
    -0.64
    ური
    -0.63
     AttributeSet
    -0.63
    odeficiency
    -0.61
    ollectionView
    -0.60
    stateProvider
    -0.60
     osobow
    -0.59
    POSITIVE LOGITS
    RegressionTest
    0.75
    Personendaten
    0.63
     CreateTagHelper
    0.61
    InSection
    0.58
     ब्रेकडाउन
    0.56
     kaarangay
    0.54
     else
    0.53
    AndEndTag
    0.52
    tanleria
    0.52
    $_['
    0.52
    Activations Density 0.420%

    No Known Activations