© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 4249
    Prev
    Next
    INDEX
    Explanations

    statements regarding the "nullable" property of data fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
    ########.
    -0.74
    Agence
    -0.71
    ENSA
    -0.71
     Mendes
    -0.70
    ::<
    -0.70
    __*/
    -0.68
     Haver
    -0.68
     _:
    -0.67
     agency
    -0.67
     Noche
    -0.66
    POSITIVE LOGITS
    stdbool
    1.00
     True
    0.85
    ArgsConstructor
    0.81
    True
    0.79
     true
    0.79
    isTrue
    0.77
    stretchr
    0.75
    TRUE
    0.73
     MessageBoxIcon
    0.73
     TextInputType
    0.73
    Activations Density 0.034%

    No Known Activations