© 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. 23-GEMMASCOPE-RES-16K
    11. 11582
    Prev
    Next
    INDEX
    Explanations

    references to specific institutions, events, or clinical studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outros
    -0.69
    存于互联网档案馆
    -0.69
    autres
    -0.65
    StoryboardSegue
    -0.65
    的其他
    -0.61
     altri
    -0.59
     poszczegól
    -0.58
     outras
    -0.56
     certains
    -0.56
     guesses
    -0.56
    POSITIVE LOGITS
     popular
    1.09
     famous
    1.06
     infamous
    1.02
     hugely
    1.01
     recently
    0.97
    popular
    0.96
     highly
    0.96
     notorious
    0.95
     famed
    0.93
     renowned
    0.93
    Activations Density 0.681%

    No Known Activations