© 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. 27-GEMMASCOPE-RES-16K
    11. 9644
    Prev
    Next
    INDEX
    Explanations

    sentences that contain punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -1.02
     nahilalakip
    -0.94
    SourceChecksum
    -0.88
    虽说
    -0.84
     defaultstate
    -0.84
    已然
    -0.81
    évaluateur
    -0.81
    ChildScrollView
    -0.80
    倘
    -0.79
    AsUp
    -0.78
    POSITIVE LOGITS
     they
    0.65
     people
    0.62
     They
    0.61
    They
    0.58
     People
    0.50
    People
    0.49
    they
    0.47
    people
    0.47
    I
    0.46
     he
    0.45
    Activations Density 0.827%

    No Known Activations