© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 48
    Prev
    Next
    INDEX
    Explanations

    references to divine authority and morality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ſche
    -0.71
     raiſ
    -0.68
     متعلقه
    -0.67
     houſe
    -0.65
     ſte
    -0.64
     purpoſe
    -0.64
     itſelf
    -0.63
    ServletConfig
    -0.63
     surla
    -0.61
     transfieras
    -0.61
    POSITIVE LOGITS
    ophores
    0.55
     dunque
    0.54
     craindre
    0.54
     ghiaccio
    0.54
     Krakowie
    0.53
     msglen
    0.52
    ؤلاء
    0.52
     vagas
    0.52
    ledes
    0.51
    Filmographie
    0.49
    Activations Density 0.132%

    No Known Activations