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

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15364
    Prev
    Next
    INDEX
    Explanations

    references to numerical data and metrics related to technical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    References/citations (e.g., [@R29], [@CR39])

    np_acts-logits-general · gemini-2.0-flash

    indication of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setopt
    -0.59
     Pense
    -0.54
     >=",
    -0.54
    localctx
    -0.52
    PerformLayout
    -0.52
     getopt
    -0.52
     mathvariant
    -0.51
    __(/*!
    -0.50
    AddRange
    -0.50
    DockStyle
    -0.50
    POSITIVE LOGITS
     measure
    0.89
     test
    0.87
    measure
    0.82
     judge
    0.78
     gauge
    0.76
     tests
    0.74
     TEST
    0.71
     Test
    0.70
    stest
    0.70
     measuring
    0.70
    Activations Density 0.132%

    No Known Activations