© 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. 30-GEMMASCOPE-RES-16K
    11. 10667
    Prev
    Next
    INDEX
    Explanations

    key points or summaries related to information and instructions

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

    Formality markers (e.g., thanking, hence, kindly)

    np_acts-logits-general · gemini-2.0-flash

    headings, lists, and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.58
     OMITBAD
    -0.56
     ujednoznacz
    -0.53
    LVANIA
    -0.49
    quared
    -0.49
    ">//
    -0.49
    таратура
    -0.47
    󠁿
    -0.47
     &___
    -0.47
    Boxscore
    -0.47
    POSITIVE LOGITS
     Hence
    0.57
    Kindly
    0.55
     hence
    0.54
    
    0.53
    noOf
    0.53
    NoOf
    0.53
     Formación
    0.50
    Thanking
    0.50
     Kindly
    0.50
    Hence
    0.49
    Activations Density 0.209%

    No Known Activations