© 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. 21-GEMMASCOPE-RES-16K
    11. 3261
    Prev
    Next
    INDEX
    Explanations

    numerical data related to percentages and statistical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HomeAsUpEnabled
    -0.64
    hyrchwyd
    -0.61
    GEBURTSDATUM
    -0.57
    ceğine
    -0.51
    AsUp
    -0.50
    Бахар
    -0.49
     localVar
    -0.48
    Życiorys
    -0.47
     FetchType
    -0.47
    rungsseite
    -0.46
    POSITIVE LOGITS
     longest
    0.37
     fresh
    0.35
     qualifi
    0.33
     almost
    0.33
     large
    0.32
     bander
    0.32
     noms
    0.31
     performances
    0.31
    ])))
    0.31
     caught
    0.30
    Activations Density 0.353%

    No Known Activations