© 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. 5727
    Prev
    Next
    INDEX
    Explanations

    the use of non-specific descriptors or terms that suggest ambiguity and complexity in ideas

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

    Follows "relatively", or "bit"

    np_acts-logits-general · gemini-2.0-flash

    degree adverbs modifying descriptions

    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
     absolutely
    -0.58
     extremely
    -0.57
     assolutamente
    -0.57
     absolutamente
    -0.56
     very
    -0.55
     ternyata
    -0.52
     apparently
    -0.51
     surely
    -0.51
     sangat
    -0.51
     absolument
    -0.51
    POSITIVE LOGITS
    tagext
    0.92
     متعلقه
    0.90
     unknownFields
    0.89
     CURIAM
    0.88
    UnusedPrivate
    0.88
    yntaxException
    0.86
     ExecuteAsync
    0.86
    PreferredItem
    0.85
    EndInit
    0.84
     оригіналу
    0.83
    Activations Density 0.139%

    No Known Activations