© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16316
    Prev
    Next
    INDEX
    Explanations

    structured data elements and types in programming languages

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

    Code or programming-related terms

    np_acts-logits-general · gemini-2.0-flash

    parsing, device performance, system calls

    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
    l
    -0.68
    -
    -0.67
     
    -0.67
    v
    -0.67
    .
    -0.66
    V
    -0.65
    h
    -0.65
    T
    -0.64
    G
    -0.64
    ,
    -0.62
    POSITIVE LOGITS
     esternos
    1.38
     ProtoMessage
    1.30
    parsedMessage
    1.28
     мәкал
    1.28
    ArgsConstructor
    1.27
    ConstraintMaker
    1.26
     Roskov
    1.26
     CreateTagHelper
    1.24
    extAlignment
    1.24
    Билгалдахарш
    1.24
    Activations Density 0.298%

    No Known Activations