© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15628
    Prev
    Next
    INDEX
    Explanations

    phrases that reference personal desires and intentions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Follows a pronoun (you, she, they, I)

    np_acts-logits-general · gemini-2.0-flash

    pronouns followed by auxiliaries or verbs

    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
    Negative Logits
     added
    -0.43
     جن
    -0.37
    دانشنامهٔ
    -0.36
     performed
    -0.35
     Dealing
    -0.35
    Dealing
    -0.34
    allclose
    -0.33
     GenerationType
    -0.33
     erfü
    -0.33
    Therefore
    -0.33
    POSITIVE LOGITS
    MessageTagHelper
    0.74
     CreateTagHelper
    0.65
    Personendaten
    0.61
     Numerade
    0.59
    Vidite
    0.56
    GEBURTSDATUM
    0.54
     pinulongan
    0.53
     Мексичка
    0.53
    FormTagHelper
    0.52
     насељу
    0.51
    Activations Density 0.206%

    No Known Activations