© 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. 3638
    Prev
    Next
    INDEX
    Explanations

    conditional statements and control flow keywords in programming code

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

    Followed by open parenthesis

    np_acts-logits-general · gemini-2.0-flash

    if followed by parenthesis

    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
    IUrlHelper
    -0.78
     Diſ
    -0.66
    TypedDataSet
    -0.66
    DeleteBehavior
    -0.65
     ſever
    -0.65
    avyzd
    -0.65
    FieldBuilder
    -0.65
    MessageTagHelper
    -0.64
     Efq
    -0.64
    SharedCtor
    -0.64
    POSITIVE LOGITS
     ("
    0.51
     "".
    0.48
     soyez
    0.48
    "".
    0.45
     !"
    0.44
     cierto
    0.43
    ]}>
    0.42
     "
    0.42
    cra
    0.41
     kebenaran
    0.40
    Activations Density 0.033%

    No Known Activations