© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 14145
    Prev
    Next
    INDEX
    Explanations

    technical keywords and comments in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.59
    latego
    -0.52
    ucap
    -0.52
    etcode
    -0.51
    ябре
    -0.48
    Халык
    -0.47
    paksa
    -0.47
    ссор
    -0.46
    babwe
    -0.46
    URIComponent
    -0.45
    POSITIVE LOGITS
     <!--
    3.25
    <!--
    1.43
    ><!--
    1.21
     nahilalakip
    1.00
    "><!--
    0.91
    <!--[
    0.90
     '{@
    0.84
    <!--
    0.81
    >{@
    0.68
    migrationBuilder
    0.68
    Activations Density 0.008%

    No Known Activations