© 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. 11-GEMMASCOPE-RES-16K
    11. 5376
    Prev
    Next
    INDEX
    Explanations

    descriptors indicating the condition and packaging of items, particularly in a sale context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/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.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.53
     surla
    -0.47
     насељу
    -0.46
    ientôt
    -0.45
     estekak
    -0.42
    riwal
    -0.42
     fVar
    -0.41
     Италијани
    -0.41
     Vordergrund
    -0.41
     inspiración
    -0.40
    POSITIVE LOGITS
     pristine
    0.68
     unopened
    0.59
     undamaged
    0.56
     untouched
    0.55
     fresh
    0.54
     fresher
    0.53
     Prist
    0.52
     unharmed
    0.51
     intact
    0.48
     virginity
    0.48
    Activations Density 0.468%

    No Known Activations