© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 1012
    Prev
    Next
    INDEX
    Explanations

    references to default settings and configurations in programming or systems context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CommandType
    -0.58
    runOnUiThread
    -0.56
     ErrIntOverflow
    -0.52
    oulli
    -0.47
     artık
    -0.47
    updateOne
    -0.46
    gonic
    -0.44
    ]+"
    -0.44
     alatt
    -0.43
    strando
    -0.43
    POSITIVE LOGITS
     initial
    1.57
     default
    1.55
     defaults
    1.49
    initial
    1.45
     초기
    1.42
     Initial
    1.42
    Initial
    1.39
     Default
    1.35
     INITIAL
    1.34
     initialize
    1.32
    Activations Density 0.355%

    No Known Activations