© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13887
    Prev
    Next
    INDEX
    Explanations

    specific numerical and measurement-related terms

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

    Quantities or dosages

    np_acts-logits-general · gemini-2.0-flash

    values with units

    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
     AssemblyTitle
    -0.75
    UrlResolution
    -0.67
     للاسماء
    -0.66
     المعيارى
    -0.62
    IsContent
    -0.54
    GOTREF
    -0.54
    ftagPool
    -0.54
    󠁧
    -0.52
    EDEFAULT
    -0.52
    featureID
    -0.50
    POSITIVE LOGITS
     depending
    0.45
     whichever
    0.43
    Depending
    0.41
     зависимости
    0.39
    MessageOf
    0.39
     Depending
    0.38
     dependiendo
    0.38
    Regardless
    0.37
    SequentialGroup
    0.36
     versions
    0.36
    Activations Density 1.094%

    No Known Activations