© 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. 10892
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with statistics or measurements

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

    Phone numbers, possibly with digits 9, 7, 5, 3, 8, 0, 2

    np_acts-logits-general · gemini-2.0-flash

    9 followed by digits or non-digits

    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
    Autoritní
    -0.44
    новниш
    -0.40
    帖最后由
    -0.39
     فريبيس
    -0.38
    writeFieldEnd
    -0.38
    SuspendLayout
    -0.38
    baric
    -0.37
    liceerd
    -0.36
     ExecuteAsync
    -0.36
    WaitGroup
    -0.35
    POSITIVE LOGITS
    httphttps
    0.56
    protoimpl
    0.48
    Vidite
    0.42
     gyhoeddwyd
    0.42
     informée
    0.41
    MutableLiveData
    0.41
    Msk
    0.40
    typeorm
    0.39
    órico
    0.39
    Palindrome
    0.39
    Activations Density 0.463%

    No Known Activations