© 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. 33-GEMMASCOPE-RES-16K
    11. 10030
    Prev
    Next
    INDEX
    Explanations

    negations and discussions around religious and ethical beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.75
    MessageTagHelper
    -0.73
    IntoConstraints
    -0.73
     GenerationType
    -0.72
    UrlResolution
    -0.67
     <<<<<<<<<<<<<<
    -0.65
    DockStyle
    -0.64
    實在
    -0.63
     '\\;'
    -0.62
    rungsseite
    -0.61
    POSITIVE LOGITS
     necessarily
    1.14
     necessariamente
    0.85
     necesariamente
    0.83
    necessarily
    0.80
     nécessairement
    0.72
     magically
    0.71
     automatically
    0.65
     exclusively
    0.62
     nødvendig
    0.58
     suddenly
    0.54
    Activations Density 1.014%

    No Known Activations