© 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. 7720
    Prev
    Next
    INDEX
    Explanations

    contact information and organizational roles in a formal context

    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
    /**
    -0.60
     $_(
    -0.55
    migrationBuilder
    -0.54
     Theſe
    -0.53
     vzduchu
    -0.53
    retudo
    -0.51
    IntoConstraints
    -0.50
     disambiguazione
    -0.50
     miniaturka
    -0.50
    NameInMap
    -0.49
    POSITIVE LOGITS
    联系人
    0.34
    DockStyle
    0.33
     manager
    0.33
     Stanton
    0.33
    联
    0.33
     Manager
    0.33
     Δ
    0.33
     contacted
    0.33
     Liberty
    0.32
     coordinator
    0.32
    Activations Density 0.150%

    No Known Activations