© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 10612
    Prev
    Next
    INDEX
    Explanations

    negative contractions, particularly in the context of personal or societal assertions

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

    Contractions with "n't" (negative auxiliary verbs)

    np_acts-logits-general · gemini-2.0-flash

    negative contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.64
     ujednoznacz
    -0.55
    EIF
    -0.51
    ,$_
    -0.51
    ″]
    -0.50
    saurus
    -0.47
     Chwiliwch
    -0.46
    jší
    -0.46
    BeNil
    -0.45
    ască
    -0.44
    POSITIVE LOGITS
    wouldn
    0.92
     doesn
    0.89
     wouldn
    0.89
     didn
    0.87
     aren
    0.87
     wasn
    0.85
    Wouldn
    0.83
     don
    0.83
    doesn
    0.83
     Didn
    0.83
    Activations Density 0.104%

    No Known Activations