© 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. 5828
    Prev
    Next
    INDEX
    Explanations

    technical terms and definitions related to software and code implementation

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

    C code #define statements

    np_acts-logits-general · gemini-2.0-flash

    define, let, and, or

    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
    +#+#
    -0.80
     Meksiku
    -0.79
     mutation
    -0.76
     margin
    -0.76
    margin
    -0.75
     Manager
    -0.75
    Museum
    -0.75
    moisture
    -0.75
     manager
    -0.74
     ProtoMessage
    -0.72
    POSITIVE LOGITS
    ########.
    0.51
    endphp
    0.48
    delige
    0.48
     Efq
    0.47
    ſelves
    0.47
     Chrif
    0.47
     itſelf
    0.46
     Anſ
    0.46
    ſelf
    0.45
     leſs
    0.45
    Activations Density 0.500%

    No Known Activations