© 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 EvalsExportsinterp-engineNEWAPI 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. 10770
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to legal claims and allegations

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

    Preceding pronouns followed by verbs indicating harm

    np_acts-logits-general · gemini-2.0-flash

    subject relied on assurances

    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
    Not in Any Lists

    No Comments

    Negative Logits
     felic
    -0.32
     lazy
    -0.31
     kav
    -0.31
    陋
    -0.31
    Converters
    -0.30
     admission
    -0.30
     avar
    -0.29
     eu
    -0.29
     ev
    -0.28
     tap
    -0.28
    POSITIVE LOGITS
     autorytatywna
    0.91
     suffers
    0.78
     suffer
    0.73
     suffered
    0.71
    __*/
    0.70
     sufre
    0.69
     suffering
    0.69
     PeEnEo
    0.68
     sufri
    0.67
    principalColumn
    0.66
    Activations Density 0.580%

    No Known Activations