© 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
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 8479
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and safety warnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iż
    -0.88
    已然
    -0.88
     requisite
    -0.85
     således
    -0.85
    AutoScaleMode
    -0.84
    这般
    -0.81
    でございます
    -0.77
     tevens
    -0.77
    Примеча
    -0.76
     nunmehr
    -0.76
    POSITIVE LOGITS
     lots
    0.74
    Lots
    0.68
     things
    0.59
     everybody
    0.58
     bigger
    0.58
     Lots
    0.57
     żeby
    0.57
     разных
    0.57
     différent
    0.56
     really
    0.56
    Activations Density 2.788%

    No Known Activations