© 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. 14-GEMMASCOPE-RES-16K
    6. 2328
    Prev
    Next
    INDEX
    Explanations

    variations of the word "lift" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -1.00
    </table>
    -0.83
     resourceCulture
    -0.79
     Castro
    -0.77
     fantasia
    -0.76
    Castro
    -0.75
     Fantasia
    -0.73
    ština
    -0.73
    alamus
    -0.73
    ganu
    -0.71
    POSITIVE LOGITS
     Gifford
    0.80
     Lift
    0.80
     LIFT
    0.74
     lifted
    0.71
     Peel
    0.70
     BCA
    0.70
     Pell
    0.70
    ACD
    0.69
     elevador
    0.68
     lifts
    0.68
    Activations Density 0.349%

    No Known Activations