© 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. 10887
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'r' in various contexts

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

    Letters "r" and "n" followed by certain characters

    np_acts-logits-general · gemini-2.0-flash

    record as

    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
    CodeAttribute
    -0.42
    :+:
    -0.40
     Tại
    -0.34
     PeEnEo
    -0.33
     أ
    -0.33
    ябре
    -0.32
    ẩy
    -0.32
    mbggenerated
    -0.32
    ához
    -0.31
    Para
    -0.31
    POSITIVE LOGITS
    ConstraintMaker
    0.62
    WithIOException
    0.56
     Vikipedi
    0.55
    发表于
    0.54
     referrerpolicy
    0.54
    FTFY
    0.51
     "..\..\
    0.48
     scolaires
    0.47
     merce
    0.46
    Хьажоргаш
    0.45
    Activations Density 0.306%

    No Known Activations