© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 14075
    Prev
    Next
    INDEX
    Explanations

    references to vulnerable populations and their risks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    consulté
    -0.56
    PYX
    -0.54
    richTextPanel
    -0.46
    crose
    -0.46
     fame
    -0.45
    ferencia
    -0.45
    cipit
    -0.45
     met
    -0.45
    同期
    -0.44
    enya
    -0.44
    POSITIVE LOGITS
     vulnerable
    0.76
    FontOfSize
    0.73
     Vulnerable
    0.70
    interopRequire
    0.64
     Elderly
    0.62
     speciale
    0.61
     speciali
    0.61
     للمعارف
    0.60
     vulné
    0.58
    DockStyle
    0.58
    Activations Density 0.276%

    No Known Activations