© 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. 126948
    Prev
    Next
    INDEX
    Explanations

    instances of string building or manipulation in code

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

    building strings programmatically

    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
    ✨:
    -0.60
     useSelector
    -0.51
     ControllerBase
    -0.51
     NavController
    -0.50
    principalColumn
    -0.49
    tagHelperRunner
    -0.49
    OrNil
    -0.48
    nonatomic
    -0.48
    Vidite
    -0.47
    TagMode
    -0.47
    POSITIVE LOGITS
    StringBuilder
    1.13
     StringBuilder
    1.00
    StringBuffer
    0.88
     StringBuffer
    0.79
    FieldBuilder
    0.64
    ChildScrollView
    0.61
    StringWriter
    0.54
    ostringstream
    0.52
    stringBuffer
    0.50
     stringBuilder
    0.49
    Activations Density 0.009%

    No Known Activations