© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 53060
    Prev
    Next
    INDEX
    Explanations

    keywords and symbols used in programming and mathematical contexts

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

    scientific and technical notation

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    DoubleQuotes
    -0.35
    <bos>
    -0.33
    Personensuche
    -0.33
    adpleegd
    -0.33
    IsContent
    -0.29
    enumii
    -0.29
     تضيفلها
    -0.28
    CppMethod
    -0.27
    BASEPATH
    -0.27
    ceğine
    -0.24
    POSITIVE LOGITS
    çim
    0.56
    richTextPanel
    0.55
    elemField
    0.55
     SEDS
    0.54
     JAXBElement
    0.54
     RemoteException
    0.52
    PostInfinity
    0.52
    fjspx
    0.51
    kháu
    0.51
    جوايز
    0.51
    Activations Density 0.129%

    No Known Activations