© 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. 16-GEMMASCOPE-RES-16K
    11. 13242
    Prev
    Next
    INDEX
    Explanations

    references to moral values and agendas in societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    opinions or perspectives

    np_acts-logits-general · gemini-2.0-flash

    abstract nouns and qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.84
     betweenstory
    -0.78
    %")
    -0.76
    serviceWorker
    -0.72
     })}
    -0.71
    tableFuture
    -0.71
     */
    -0.71
    __":
    -0.70
    Демографія
    -0.70
    Viitteet
    -0.69
    POSITIVE LOGITS
     estekak
    0.66
     been
    0.59
     nodig
    0.53
     had
    0.51
    Autoritní
    0.50
    k
    0.48
     Anteil
    0.47
     
    0.46
     backing
    0.46
     experience
    0.45
    Activations Density 0.642%

    No Known Activations