© 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. 5-GEMMASCOPE-RES-16K
    11. 5520
    Prev
    Next
    INDEX
    Explanations

    expressions of possession or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     meriva
    -0.72
     lamella
    -0.66
     abbildung
    -0.66
    ignoire
    -0.65
     octaves
    -0.64
     betweenstory
    -0.64
     omnia
    -0.63
     jaya
    -0.63
     Hodgkin
    -0.63
    INSEE
    -0.63
    POSITIVE LOGITS
     been
    1.22
     not
    1.12
     gonna
    0.96
     also
    0.95
     really
    0.94
    '])
    0.93
    "])
    0.92
    s
    0.92
     a
    0.91
     is
    0.91
    Activations Density 0.199%

    No Known Activations