© 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. 25-GEMMASCOPE-RES-16K
    11. 2452
    Prev
    Next
    INDEX
    Explanations

    expressions related to installation and setup procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     terlebih
    -0.71
    Билгалдахарш
    -0.66
     оригіналу
    -0.57
     first
    -0.56
    ISupport
    -0.55
     sondern
    -0.53
    Begriffsklä
    -0.51
    ]<<"
    -0.51
     Normdatei
    -0.50
    也想
    -0.49
    POSITIVE LOGITS
     voila
    1.52
    Voila
    1.32
     voilà
    1.30
     Voilà
    1.20
     Done
    1.16
    Voilà
    1.13
     presto
    1.09
     boom
    1.07
     viola
    1.06
     DONE
    1.05
    Activations Density 0.365%

    No Known Activations