© 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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 9508
    Prev
    Next
    INDEX
    Explanations

    references to different universes and multiverse concepts

    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
    rungsseite
    -0.51
     Comprometido
    -0.46
    ONSORED
    -0.44
    btnAdd
    -0.44
     sponsors
    -0.43
    ‍♀️
    -0.42
     Artículos
    -0.42
    PATRICK
    -0.41
     pintor
    -0.40
    sponsor
    -0.39
    POSITIVE LOGITS
     universe
    0.91
     Universe
    0.86
    Universe
    0.77
     realm
    0.76
    universe
    0.73
     universes
    0.70
    realm
    0.68
     galaxy
    0.66
     realms
    0.66
     spacetime
    0.66
    Activations Density 0.842%

    No Known Activations