© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15260
    Prev
    Next
    INDEX
    Explanations

    expressions related to sociopolitical opinions and discourse

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

    Contradictory or disagreeable statements

    np_acts-logits-general · gemini-2.0-flash

    I do not want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.77
     հղումներ
    -0.70
    rungsseite
    -0.67
    rrggbb
    -0.66
     Picchu
    -0.65
    Попис
    -0.65
    Autoritní
    -0.65
    bcryptjs
    -0.64
    нгред
    -0.62
     propOrder
    -0.62
    POSITIVE LOGITS
     I
    0.38
     
    0.35
     blind
    0.35
     who
    0.31
     blinded
    0.30
     racist
    0.29
     this
    0.29
     his
    0.28
    comment
    0.28
    em
    0.28
    Activations Density 0.510%

    No Known Activations