© 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. 9-GEMMASCOPE-RES-131K
    6. 45564
    Prev
    Next
    INDEX
    Explanations

    phrases that denote regulations or conditions outlined in legal or formal contexts

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

    under followed by a noun or phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RefNanny
    -0.50
     Numerade
    -0.47
    =$?
    -0.45
     فريبيس
    -0.45
    rebro
    -0.44
     Breite
    -0.44
     Braga
    -0.43
    Materiaal
    -0.43
     oignon
    -0.42
    phemy
    -0.42
    POSITIVE LOGITS
    Under
    1.17
     Under
    1.16
    under
    0.74
     UNDER
    0.73
    UNDER
    0.69
     under
    0.60
    Под
    0.58
     Під
    0.56
     Unter
    0.55
    Unter
    0.54
    Activations Density 0.018%

    No Known Activations