© 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. 30-GEMMASCOPE-RES-16K
    11. 11215
    Prev
    Next
    INDEX
    Explanations

    desires or intentions related to trying new things or making proposals

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

    Preceding "to" or a letter

    np_acts-logits-general · gemini-2.0-flash

    desirable to try

    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
     currently
    -0.57
     kadang
    -0.56
    tissimi
    -0.54
     parfois
    -0.53
     often
    -0.53
     übrigens
    -0.52
     oftentimes
    -0.51
     attualmente
    -0.51
     Currently
    -0.51
     sometimes
    -0.51
    POSITIVE LOGITS
     something
    0.54
     pudesse
    0.54
    something
    0.51
    Something
    0.50
    رشف
    0.48
     debía
    0.48
    djangoproject
    0.47
    何とか
    0.47
     somehow
    0.47
     SOMETHING
    0.46
    Activations Density 0.491%

    No Known Activations