© 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. 14712
    Prev
    Next
    INDEX
    Explanations

    phrases indicating manipulation or misuse of organizations

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

    "... way" or "... manner"

    np_acts-logits-general · gemini-2.0-flash

    way or manner

    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
    izacja
    -0.35
     Autorisations
    -0.33
     зрения
    -0.33
    zionata
    -0.33
     sharpen
    -0.32
    izacji
    -0.32
    dflare
    -0.31
     statistics
    -0.31
     internes
    -0.30
     repatriation
    -0.30
    POSITIVE LOGITS
     way
    1.91
     manner
    1.70
     ways
    1.65
     manière
    1.36
    manner
    1.34
     manera
    1.31
    Way
    1.30
     façon
    1.30
     maneira
    1.29
     WAY
    1.28
    Activations Density 0.320%

    No Known Activations