© 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. 28-GEMMASCOPE-RES-16K
    11. 9603
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of maximizing efficiency or capability

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

    "As" followed by a word indicating possibility

    np_acts-logits-general · gemini-2.0-flash

    as X as Y

    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
    Бахар
    -0.49
    Personendaten
    -0.45
    Geplaatst
    -0.43
    findpost
    -0.43
     AssemblyProduct
    -0.39
    采
    -0.39
     pinulongan
    -0.38
    postsleuth
    -0.38
    脚注の使い方
    -0.38
     متعلقه
    -0.38
    POSITIVE LOGITS
     feasible
    0.86
     practicable
    0.82
     permitted
    0.80
     allowable
    0.73
     permitting
    0.70
     permissible
    0.69
     permits
    0.69
     raisonnable
    0.67
     available
    0.67
     poffible
    0.67
    Activations Density 0.219%

    No Known Activations