© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7242
    Prev
    Next
    INDEX
    Explanations

    references to sports team performance and playoff scenarios

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

    math or standings

    np_acts-logits-general · gemini-2.0-flash

    mathematical standings and outcomes

    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
    úblico
    -0.43
     Phry
    -0.40
    Personendaten
    -0.39
     FEDERAL
    -0.39
    pour
    -0.38
    spora
    -0.38
     SWEET
    -0.37
     warden
    -0.37
    ("'"
    -0.37
     Mikro
    -0.37
    POSITIVE LOGITS
     mathematically
    0.57
     noDo
    0.56
     matemática
    0.53
     clinched
    0.47
     mathematical
    0.47
     springfox
    0.47
    mathematical
    0.45
     Mathemat
    0.45
    protoimpl
    0.45
     mathe
    0.44
    Activations Density 0.102%

    No Known Activations