© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11406
    Prev
    Next
    INDEX
    Explanations

    specific terms related to academic or professional publications

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

    following numbers

    np_acts-logits-general · gemini-2.0-flash

    molecules, improved, study

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    contentLoaded
    -0.71
    tagHelperRunner
    -0.60
    mybatisplus
    -0.59
    classID
    -0.55
    يكب
    -0.54
    NameInMap
    -0.52
     estekak
    -0.52
     InputDecoration
    -0.49
     kaarangay
    -0.48
    expandindo
    -0.48
    POSITIVE LOGITS
     paš
    0.38
     yürü
    0.35
     Rücken
    0.34
     orejas
    0.34
    wiąz
    0.33
     Bewußt
    0.33
     vengan
    0.32
     terciopelo
    0.32
     Unterneh
    0.32
     yö
    0.32
    Activations Density 1.444%

    No Known Activations