© 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. 5034
    Prev
    Next
    INDEX
    Explanations

    references to sentences and their structural components in the context of measurement or legal terminology

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

    Text snippets containing "Quote"

    np_acts-logits-general · gemini-2.0-flash

    quotes and definitions or descriptions

    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
    multer
    -0.54
    ihnach
    -0.53
    shiro
    -0.53
    IBC
    -0.53
    PBT
    -0.49
     HomeController
    -0.48
     TextInputType
    -0.48
    Leisure
    -0.47
     estekak
    -0.46
    فض
    -0.46
    POSITIVE LOGITS
     ExecuteAsync
    0.50
     Song
    0.50
     Equation
    0.47
     pattern
    0.47
     patterns
    0.46
     PyTuple
    0.44
     mosa
    0.44
    yntaxException
    0.42
     SONG
    0.42
     Recipe
    0.42
    Activations Density 0.616%

    No Known Activations