© 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. 12429
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns expressing personal opinions or experiences

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

    First-person statements of fondness

    np_acts-logits-general · gemini-2.0-flash

    expressing personal fondness

    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
     Италијани
    -0.51
    Initializable
    -0.50
     ErrIntOverflow
    -0.46
    Хьажоргаш
    -0.45
    السكان
    -0.45
    elemField
    -0.44
     againſt
    -0.42
     kasarigan
    -0.42
    énario
    -0.41
     iNdEx
    -0.41
    POSITIVE LOGITS
     love
    0.67
     adore
    0.63
     fondness
    0.60
     fascination
    0.59
     admire
    0.59
     adored
    0.59
     admired
    0.57
     fascinated
    0.57
    いつか
    0.57
     always
    0.56
    Activations Density 0.381%

    No Known Activations