© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 27-GEMMASCOPE-RES-16K
    11. 10687
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or references to specific "the" entities and collective nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteBehavior
    -0.66
     виправивши
    -0.61
     defaultstate
    -0.60
    ########.
    -0.60
    recated
    -0.59
    erçe
    -0.59
    tagHelperRunner
    -0.55
    PERTIES
    -0.55
    Географиясе
    -0.55
    hoeddwyd
    -0.54
    POSITIVE LOGITS
     behalf
    0.89
     verge
    0.51
     heels
    0.48
     side
    0.43
     basis
    0.43
     sidelines
    0.43
     outskirts
    0.41
     occasion
    0.40
     brink
    0.40
     edge
    0.38
    Activations Density 0.160%

    No Known Activations