© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14082
    Prev
    Next
    INDEX
    Explanations

    code elements related to the definition and manipulation of graphical shapes

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

    Code or commands followed by user

    np_acts-logits-general · gemini-2.0-flash

    user turn starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     gyhoeddwyd
    -0.56
    GEBURTS
    -0.54
    cookieParser
    -0.54
     MainAxisSize
    -0.51
     partij
    -0.50
    礴
    -0.49
    CloseOperation
    -0.46
    laught
    -0.46
     WebDriverWait
    -0.46
    setVerticalGroup
    -0.45
    POSITIVE LOGITS
     ihm
    0.38
    OrUpdate
    0.38
     mie
    0.36
    =$((
    0.36
     MacGregor
    0.35
    뀜
    0.35
     calific
    0.34
    دانشنامهٔ
    0.34
    ihr
    0.34
     personalize
    0.33
    Activations Density 0.116%

    No Known Activations