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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 335
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures, especially those related to networking and APIs

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

    Code, imports, or start of turn

    np_acts-logits-general · gemini-2.0-flash

    user input

    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
    存于互联网档案馆
    -0.47
    Transkript
    -0.45
    DrawerToggle
    -0.42
    ReusableCell
    -0.41
     ويكيميديا
    -0.41
    PORTE
    -0.40
    GeneratedMessage
    -0.38
    WriteBarrier
    -0.38
    Witam
    -0.37
     كومونز
    -0.37
    POSITIVE LOGITS
     cathédrale
    0.51
    ThroughAttribute
    0.50
    Jereo
    0.50
    OOTDTY
    0.49
    SceneManagement
    0.47
     Италијани
    0.45
    NameInMap
    0.45
     okuyayım
    0.45
    rungsseite
    0.44
    mbggenerated
    0.44
    Activations Density 0.107%

    No Known Activations