© 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. 4-GEMMASCOPE-RES-16K
    6. 3012
    Prev
    Next
    INDEX
    Explanations

    numerical values and symbols related to scientific data or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.74
    fromnode
    -0.67
     accett
    -0.66
    IBOutlet
    -0.56
     accepté
    -0.55
     judicia
    -0.55
     hjär
    -0.54
    ooker
    -0.54
     débar
    -0.53
     âmes
    -0.53
    POSITIVE LOGITS
    Personendaten
    0.83
     newOwner
    0.69
    IsMutable
    0.63
     [*]
    0.57
     فريبيس
    0.56
    InstrumentedTest
    0.54
    CodedInputStream
    0.54
    WriteBarrier
    0.53
     intptr
    0.51
     Highlands
    0.51
    Activations Density 1.252%

    No Known Activations