© 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. 14-GEMMASCOPE-RES-16K
    11. 5389
    Prev
    Next
    INDEX
    Explanations

    negative or opposing statements regarding human nature and social constructs

    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
     intptr
    -0.63
    exitRule
    -0.63
    icose
    -0.62
    *}$
    -0.62
     يتيمه
    -0.61
     Италијани
    -0.61
     <=",
    -0.59
    ValueStyle
    -0.59
     }));
    -0.58
     Приступљено
    -0.57
    POSITIVE LOGITS
    Actual
    0.51
     Actual
    0.51
    AddTagHelper
    0.51
     tatsäch
    0.48
     Honest
    0.48
    真实的
    0.48
     WARRANT
    0.48
     marcador
    0.48
    bootstrapcdn
    0.48
    actual
    0.48
    Activations Density 0.401%

    No Known Activations