© 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. 1888
    Prev
    Next
    INDEX
    Explanations

    conditional and operational phrases related to function calls in programming

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

    "single" or "one"

    np_acts-logits-general · gemini-2.0-flash

    single item or one

    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
     समीक्षाओं
    -0.42
    liothèque
    -0.41
    makeText
    -0.41
    __*/
    -0.40
    FromArgb
    -0.38
    ttemberg
    -0.36
    ">//
    -0.35
    âce
    -0.35
    lierten
    -0.34
    不信
    -0.34
    POSITIVE LOGITS
     single
    2.05
    single
    1.98
    Single
    1.82
    SINGLE
    1.69
     SINGLE
    1.68
     Single
    1.67
     tunggal
    1.51
     één
    1.51
     one
    1.43
     ONE
    1.40
    Activations Density 0.650%

    No Known Activations