© 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. 9792
    Prev
    Next
    INDEX
    Explanations

    technical or specialized terms related to scientific or medical processes

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

    Comes before capitalized words

    np_acts-logits-general · gemini-2.0-flash

    academic findings and reports

    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
    glEnd
    -0.62
    ρ
    -0.61
    an
    -0.51
    ól
    -0.49
     Rowe
    -0.45
     cuchara
    -0.45
    kal
    -0.44
     Blom
    -0.43
    AN
    -0.43
    R
    -0.42
    POSITIVE LOGITS
    this
    1.04
     this
    1.03
     EconPapers
    0.98
    self
    0.97
     self
    0.97
     الرياضيه
    0.86
     typelib
    0.81
    WithFormat
    0.81
    PerformLayout
    0.78
     referenties
    0.77
    Activations Density 0.062%

    No Known Activations