© 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. 7143
    Prev
    Next
    INDEX
    Explanations

    array indexing and method invocation in a programming context

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

    Code, equations, or unusual syntax

    np_acts-logits-general · gemini-2.0-flash

    code assignment or condition

    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
    -
    -0.53
    <i>
    -0.52
    ↵
    -0.50
    ↵↵
    -0.50
     long
    -0.47
    察
    -0.46
     J
    -0.46
    的多
    -0.46
     modified
    -0.46
    2
    -0.46
    POSITIVE LOGITS
    tagHelperRunner
    1.15
     للاسماء
    1.15
     فريبيس
    1.10
     مشين
    1.08
     وتسجيلات
    1.08
    parsedMessage
    1.07
    principalColumn
    1.05
    NameInMap
    1.04
    StoryboardSegue
    1.03
     ujednoznacz
    1.01
    Activations Density 0.224%

    No Known Activations