© 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. 16319
    Prev
    Next
    INDEX
    Explanations

    product features related to convenience and functionality in baby items

    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
     bowiem
    -0.40
     therefore
    -0.39
     signifie
    -0.39
     czł
    -0.37
     således
    -0.36
    
    -0.36
     approximately
    -0.36
     cannot
    -0.35
     fotografii
    -0.35
     actualidad
    -0.35
    POSITIVE LOGITS
    +#+#
    0.81
     crappy
    0.75
     stuff
    0.74
     gonna
    0.71
     messing
    0.70
     messed
    0.68
     nicer
    0.68
     kinda
    0.67
     nakalista
    0.67
     fuckin
    0.66
    Activations Density 0.486%

    No Known Activations