© 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. 7870
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate additional information or emphasize various points in a discussion

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

    Text following transition words

    np_acts-logits-general · gemini-2.0-flash

    introducing further information

    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
     først
    -0.60
    まずは
    -0.60
     nonetheless
    -0.56
     primarily
    -0.56
     nevertheless
    -0.56
    primarily
    -0.55
     eerst
    -0.55
     ابتدا
    -0.54
    icitis
    -0.54
    首先
    -0.53
    POSITIVE LOGITS
    Personendaten
    0.38
     added
    0.38
    postsleuth
    0.36
     ditambah
    0.35
     informée
    0.35
     engraçadas
    0.34
    Legături
    0.33
     fordi
    0.33
    arXiv
    0.33
    ężczy
    0.33
    Activations Density 0.475%

    No Known Activations