© 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. 31-GEMMASCOPE-RES-16K
    11. 3010
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "I" and related forms to identify personal opinions or beliefs

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

    first-person singular pronouns and expressions of personal opinion or belief.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    EndInit
    -0.58
    RegistryLite
    -0.44
     uſe
    -0.44
    Identyfik
    -0.43
     poffible
    -0.41
    saco
    -0.41
     leſs
    -0.40
     Vanguard
    -0.40
     fhall
    -0.39
     vagab
    -0.39
    POSITIVE LOGITS
     personally
    0.63
     المعيارى
    0.56
    webElementXpaths
    0.51
     personalmente
    0.48
    +#+#
    0.47
     expects
    0.47
    IUrlHelper
    0.46
     predicts
    0.46
     overheard
    0.44
     persönlich
    0.43
    Activations Density 0.320%

    No Known Activations