© 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. 10673
    Prev
    Next
    INDEX
    Explanations

    statements that provide guidance or instructions to individuals

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

    Following "you" (often leads to advice or suggestions)

    np_acts-logits-general · gemini-2.0-flash

    you can

    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
    EDEFAULT
    -0.55
    Географиясе
    -0.54
    లాలు
    -0.46
    ۜ
    -0.46
     sih
    -0.43
    ksikon
    -0.43
     uintptr
    -0.43
    sizeCache
    -0.43
    mtrl
    -0.43
    autaire
    -0.42
    POSITIVE LOGITS
     need
    0.47
     can
    0.45
     mustn
    0.41
    SourceChecksum
    0.40
     must
    0.40
    :✨
    0.40
    DispatchToProps
    0.39
     gotta
    0.39
     gonna
    0.38
    要知道
    0.38
    Activations Density 0.148%

    No Known Activations