© 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. 20-GEMMASCOPE-RES-16K
    11. 11291
    Prev
    Next
    INDEX
    Explanations

    variable assignments and object properties in code snippets

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

    Iterating through arrays, often with "i"

    np_acts-logits-general · gemini-2.0-flash

    accessing elements in collections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.44
    доби
    -0.43
     pl
    -0.41
     first
    -0.41
    既
    -0.40
    б
    -0.40
     alone
    -0.40
     void
    -0.39
     نخ
    -0.38
     Based
    -0.38
    POSITIVE LOGITS
     المعيارى
    1.07
     objectAtIndex
    0.86
    Personendaten
    0.85
    AddTagHelper
    0.85
    AddHtmlAttribute
    0.83
    RectangleBorder
    0.82
    ValueStyle
    0.81
    MLLoader
    0.80
    '][$
    0.80
     Италијани
    0.79
    Activations Density 0.373%

    No Known Activations