© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12254
    Prev
    Next
    INDEX
    Explanations

    expressions of love and appreciation for experiences, particularly involving wine

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

    Followed by uppercase letters or punctuation

    np_acts-logits-general · gemini-2.0-flash

    expression of surprise or conclusion

    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
    setVerticalGroup
    -0.55
    SerializedSize
    -0.50
    новништво
    -0.47
    MENAFN
    -0.46
    Geografía
    -0.46
     infatti
    -0.46
    ANZE
    -0.46
     dessutom
    -0.45
    AnchorStyles
    -0.45
    MergeFrom
    -0.45
    POSITIVE LOGITS
    感想
    0.59
    不得不说
    0.57
    Fazit
    0.57
     wow
    0.56
    WOW
    0.56
     WOW
    0.56
    Wow
    0.54
     Wow
    0.53
     frankly
    0.53
    wow
    0.50
    Activations Density 0.295%

    No Known Activations