© 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
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 12903
    Prev
    Next
    INDEX
    Explanations

    terms related to nuclear energy and its development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rot
    -0.44
     ér
    -0.40
    ように
    -0.39
     pole
    -0.38
    路
    -0.38
    ומות
    -0.38
    Rot
    -0.37
    rot
    -0.37
    早
    -0.37
    reverse
    -0.37
    POSITIVE LOGITS
     nuclear
    1.11
     Nuclear
    1.07
    Nuclear
    1.04
     nucléaire
    0.98
    nuclear
    0.90
     NUCLEAR
    0.89
     IAEA
    0.76
     radioactive
    0.73
     Atomic
    0.71
     nuke
    0.70
    Activations Density 0.401%

    No Known Activations