© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14560
    Prev
    Next
    INDEX
    Explanations

    phrases related to political accountability and responses to corruption

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

    Negative sentiment/corruption

    np_acts-logits-general · gemini-2.0-flash

    leniency for wrongdoing

    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
    yntaxException
    -0.62
    awtextra
    -0.58
    RTEX
    -0.56
     يتيمه
    -0.53
    parsedMessage
    -0.51
    prepareStatement
    -0.50
    ReusableCell
    -0.49
    Hentet
    -0.48
    \"");
    -0.48
     مشارکت‌کنندگان
    -0.48
    POSITIVE LOGITS
     perverse
    0.38
     gevaar
    0.37
     camuf
    0.36
     impunity
    0.33
     loopholes
    0.32
     peligro
    0.31
    jsii
    0.31
     dangerous
    0.31
     peggio
    0.31
    laş
    0.30
    Activations Density 0.766%

    No Known Activations