© 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. 15006
    Prev
    Next
    INDEX
    Explanations

    conditional statements and structure within code

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

    Code containing "if" statements

    np_acts-logits-general · gemini-2.0-flash

    conditional statements

    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
     lo
    -0.49
    Filmografia
    -0.49
    tiary
    -0.46
    laris
    -0.45
    IONA
    -0.44
     vägen
    -0.44
    Teilen
    -0.43
    endfor
    -0.43
     Américas
    -0.43
    tares
    -0.43
    POSITIVE LOGITS
     تضيفلها
    0.87
     Audiodateien
    0.84
    !*\
    0.74
    Geplaatst
    0.74
    MessageTagHelper
    0.73
     esternos
    0.72
     <=",
    0.72
     estekak
    0.70
    sizeCache
    0.69
    FieldBuilder
    0.69
    Activations Density 0.068%

    No Known Activations