© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8047
    Prev
    Next
    INDEX
    Explanations

    references to community gatherings and communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.60
     disambiguazione
    -0.59
     resourceCulture
    -0.55
    outWeight
    -0.55
     Мексичка
    -0.51
     newBuilder
    -0.51
    tagHelperRunner
    -0.51
    ">//
    -0.51
     SqlParameter
    -0.50
    новништво
    -0.50
    POSITIVE LOGITS
     Torah
    0.81
     Jewish
    0.78
     Rabbi
    0.77
    Jewish
    0.69
     Talmud
    0.68
    Rabbi
    0.68
     rabb
    0.67
     Yiddish
    0.65
     rabbi
    0.63
     Orthodox
    0.63
    Activations Density 0.077%

    No Known Activations