© 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. 8086
    Prev
    Next
    INDEX
    Explanations

    references to programming terminology and coding concepts

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

    Code, variables, or properties in multiple languages

    np_acts-logits-general · gemini-2.0-flash

    variable, property, lines, solution

    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
     himself
    -1.04
    himself
    -0.72
     his
    -0.70
     Himself
    -0.69
     koji
    -0.65
     său
    -0.65
     Jr
    -0.59
    Completo
    -0.57
    彼は
    -0.56
     ktorý
    -0.52
    POSITIVE LOGITS
     herself
    1.14
    herself
    0.97
     koja
    0.74
     která
    0.72
     która
    0.71
     ktorá
    0.68
     которую
    0.66
     која
    0.64
     została
    0.63
     kterou
    0.63
    Activations Density 2.212%

    No Known Activations