© 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. 18-GEMMASCOPE-RES-16K
    11. 215
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords

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

    Code, identifiers, and technical terms

    np_acts-logits-general · gemini-2.0-flash

    mathematical or technical terms

    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
    RenderAtEndOf
    -0.87
    PerformLayout
    -0.83
    TagHelper
    -0.82
     المعيارى
    -0.78
    protoimpl
    -0.78
    ViewFeatures
    -0.75
    awtextra
    -0.75
     calendriers
    -0.74
    tvguidetime
    -0.74
     [][]
    -0.73
    POSITIVE LOGITS
    netje
    0.50
    styrelsen
    0.48
     animés
    0.48
     nélk
    0.47
     aikaa
    0.47
     identifiés
    0.44
    getahuan
    0.43
     fermée
    0.43
     próprias
    0.43
     fermés
    0.42
    Activations Density 0.250%

    No Known Activations