© 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. 28-GEMMASCOPE-RES-16K
    11. 5087
    Prev
    Next
    INDEX
    Explanations

    complex relationships in collaborative networks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Pairwise relationships or interactions

    np_acts-logits-general · gemini-2.0-flash

    pairwise relationships and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ActionCreators
    -0.56
    IsMutable
    -0.49
    PerformLayout
    -0.48
     المعيارى
    -0.45
     propOrder
    -0.41
    AxisAlignment
    -0.41
     Normdatei
    -0.41
     auprès
    -0.40
    quisar
    -0.40
    ViewHolder
    -0.40
    POSITIVE LOGITS
     mutual
    1.05
     pairwise
    1.04
     pair
    1.01
     pairs
    0.98
     pairing
    0.95
     pairings
    0.92
     between
    0.90
     inter
    0.90
    同士
    0.89
    Pair
    0.88
    Activations Density 2.183%

    No Known Activations