© 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. 15774
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue and statements expressing opinions or information

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

    something said or communicated

    np_acts-logits-general · gemini-2.0-flash

    statements and expressions

    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
    nonatomic
    -0.29
    sizeCache
    -0.28
    zogen
    -0.28
    錨
    -0.27
     Wicidata
    -0.27
     useState
    -0.27
     généraux
    -0.27
    :+:
    -0.26
    fpm
    -0.26
     laikā
    -0.25
    POSITIVE LOGITS
     speaks
    1.56
     speak
    1.48
     Speak
    1.28
     Speaks
    1.27
    speak
    1.24
    Speak
    1.22
     speaking
    1.05
     spoke
    1.03
    speaking
    0.99
    spoke
    0.94
    Activations Density 0.217%

    No Known Activations