© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8090
    Prev
    Next
    INDEX
    Explanations

    elements related to programs or initiatives involving collaboration, community involvement, or organizational participation

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

    a specific "program"

    np_acts-logits-general · gemini-2.0-flash

    program

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    jenost
    -0.47
    ASTNode
    -0.42
     SPOILERS
    -0.41
    Claro
    -0.41
    Spoilers
    -0.41
    SocketAddress
    -0.40
    ceus
    -0.39
     Theor
    -0.39
     kone
    -0.39
    tsen
    -0.39
    POSITIVE LOGITS
     program
    2.85
     programme
    2.64
    program
    2.44
     programs
    2.39
     Program
    2.35
     programmes
    2.29
     programa
    2.25
    Program
    2.22
     Programme
    2.20
     PROGRAM
    2.16
    Activations Density 0.393%

    No Known Activations