© 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. 16-GEMMASCOPE-RES-16K
    11. 9186
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements, particularly those related to variable assignments and function definitions

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

    Code snippets and programming terms

    np_acts-logits-general · gemini-2.0-flash

    code initializers and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zurück
    -0.49
     return
    -0.44
    return
    -0.41
    icht
    -0.39
    /$',
    -0.39
     returning
    -0.38
     Return
    -0.38
     Zurück
    -0.37
    Collapsed
    -0.36
     pavo
    -0.35
    POSITIVE LOGITS
     للاسماء
    0.89
     ویکی‌پدیا
    0.85
     AssemblyCulture
    0.85
    MigrationBuilder
    0.84
    /**
    0.82
    Билгалдахарш
    0.79
     дописавши
    0.78
     kasarigan
    0.75
    MemoryWarning
    0.74
    NOPQRST
    0.74
    Activations Density 0.079%

    No Known Activations