© 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. 9788
    Prev
    Next
    INDEX
    Explanations

    terms related to industrial activities and industries

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

    "Industrial"

    np_acts-logits-general · gemini-2.0-flash

    industrial and related contexts

    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
     ***!
    -0.77
    MemoryWarning
    -0.71
    MigrationBuilder
    -0.70
    ImageContext
    -0.69
    mockito
    -0.69
     HttpHeaders
    -0.68
     المعيارى
    -0.67
    kuuta
    -0.66
    principalColumn
    -0.64
    bootstrapcdn
    -0.64
    POSITIVE LOGITS
     Industrial
    0.64
     industrial
    0.64
    Industrial
    0.57
    seigneur
    0.56
    hartt
    0.56
    industrial
    0.53
     INDUSTRIAL
    0.51
     *@
    0.51
    romes
    0.48
     Throwable
    0.47
    Activations Density 0.046%

    No Known Activations