© 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. 28-GEMMASCOPE-RES-16K
    11. 3706
    Prev
    Next
    INDEX
    Explanations

    expressions of desire and need for personal fulfillment and creativity

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

    Sentences expressing desire or wanting

    np_acts-logits-general · gemini-2.0-flash

    wanting to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.68
    rungsseite
    -0.68
    ValueStyle
    -0.63
    GenerationType
    -0.62
     Walkover
    -0.61
    
    -0.57
    stateMutability
    -0.55
    BeginInit
    -0.53
    الحياه
    -0.53
    makeConstraints
    -0.52
    POSITIVE LOGITS
     wanting
    0.65
     want
    0.60
     wants
    0.59
     wanted
    0.54
     deseo
    0.52
     desire
    0.51
    want
    0.51
     desperately
    0.51
     WANT
    0.50
     ingin
    0.49
    Activations Density 0.264%

    No Known Activations