© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14924
    Prev
    Next
    INDEX
    Explanations

    mathematical or logical structures and relationships in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     AssemblyCompany
    -0.43
    featureID
    -0.41
    GIVEREF
    -0.39
     utafitiHapana
    -0.37
     الاطلاع
    -0.37
     gethan
    -0.37
    writeFieldEnd
    -0.37
     Quarantine
    -0.36
    Демографія
    -0.36
     AssemblyProduct
    -0.35
    POSITIVE LOGITS
     jointly
    0.71
     joint
    0.61
     gemeinsamen
    0.56
     gemeinsame
    0.56
    Joint
    0.54
     common
    0.54
     gemens
    0.54
    joint
    0.53
     Joint
    0.51
    お互
    0.51
    Activations Density 0.785%

    No Known Activations