© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 7698
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and structure, particularly in the context of validation rules and attributes in code

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

    user input or conditions

    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
     betweenstory
    -0.63
    الحياه
    -0.56
     MainAxisSize
    -0.53
     HttpNotFound
    -0.49
     سكانية
    -0.44
     armées
    -0.42
     Biôgrafia
    -0.42
    fillType
    -0.40
    səhifə
    -0.40
     lumineux
    -0.40
    POSITIVE LOGITS
     Validators
    0.60
    makeConstraints
    0.59
    DataAnnotations
    0.51
    inSlope
    0.51
     conditions
    0.49
    validates
    0.48
    ConstraintMaker
    0.47
    IntoConstraints
    0.45
    andExpect
    0.45
    HtmlAttribute
    0.45
    Activations Density 0.001%

    No Known Activations