© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 78353
    Prev
    Next
    INDEX
    Explanations

    words related to safety, security, and anxiety

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

    "An" followed by names or legal codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    före
    -0.47
     Bidang
    -0.44
     Rodrig
    -0.42
     Meksi
    -0.42
    lrrr
    -0.41
     jota
    -0.41
    Rodrigo
    -0.41
     imprensa
    -0.40
     Tagore
    -0.40
     niitä
    -0.39
    POSITIVE LOGITS
    安
    1.95
     安
    1.60
    안
    1.22
     안
    1.21
     An
    0.86
    An
    0.76
     Ан
    0.75
    安心
    0.74
    SAFETY
    0.73
     AN
    0.72
    Activations Density 0.002%

    No Known Activations