© 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. 15354
    Prev
    Next
    INDEX
    Explanations

    code snippets related to event handling in a programming context

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

    Code or text followed by "is"

    np_acts-logits-general · gemini-2.0-flash

    is never

    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
    yntaxException
    -0.61
    大
    -0.60
     المعيارى
    -0.59
    principalColumn
    -0.59
    SPATH
    -0.57
    Портал
    -0.57
    Impro
    -0.56
    riez
    -0.55
    yves
    -0.52
    xffffffff
    -0.52
    POSITIVE LOGITS
    
    0.52
    TemporalType
    0.51
     Ohren
    0.48
     aank
    0.46
    ExtendWith
    0.45
     Universitaria
    0.45
     Universitario
    0.45
     ISNI
    0.45
    Activator
    0.44
     توانند
    0.44
    Activations Density 0.431%

    No Known Activations