© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4160
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements, particularly related to function declarations and control structures

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

    Code or URL parsing-related tokens

    np_acts-logits-general · gemini-2.0-flash

    module addresses and code parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.48
    iastes
    -0.45
     lisäksi
    -0.39
    httphttps
    -0.38
     jScrollPane
    -0.38
    出版年
    -0.38
    expandindo
    -0.38
    queles
    -0.37
     jspb
    -0.37
    heça
    -0.36
    POSITIVE LOGITS
     незавершена
    0.54
     препратки
    0.53
     censiti
    0.50
    Slf
    0.46
    enne
    0.42
     Audiodateien
    0.42
     OFDb
    0.42
    inn
    0.40
     ent
    0.40
     Dunn
    0.40
    Activations Density 0.101%

    No Known Activations