© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 102165
    Prev
    Next
    INDEX
    Explanations

    conditions that check for emptiness in data structures

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

    isEmpty

    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
    Slf
    -0.62
     oprot
    -0.59
    Brun
    -0.59
    Greg
    -0.58
    Ramon
    -0.57
    Alan
    -0.55
    David
    -0.55
     Buk
    -0.55
     Bron
    -0.54
     boat
    -0.53
    POSITIVE LOGITS
    isEmpty
    1.23
     isEmpty
    1.07
    OrWhiteSpace
    0.58
    IsEmpty
    0.57
     autorytatywna
    0.54
    isNotEmpty
    0.49
    IsNullOrEmpty
    0.48
     HasFactory
    0.48
     mergeFrom
    0.47
     HttpNotFound
    0.45
    Activations Density 0.002%

    No Known Activations