© 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. 5245
    Prev
    Next
    INDEX
    Explanations

    sections and organizational elements within a research paper or academic article

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

    Sections, discussing, reviewing, demonstrating, describing

    np_acts-logits-general · gemini-2.0-flash

    discuss or demonstrate research findings

    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
     autorytatywna
    -0.63
    OCCURRED
    -0.57
    IsContent
    -0.55
     utafitiHapana
    -0.53
    DbType
    -0.53
     Numerade
    -0.50
    böz
    -0.48
     iconst
    -0.48
     leaſt
    -0.47
    GEBURTSDATUM
    -0.47
    POSITIVE LOGITS
     discusses
    0.84
     discuss
    0.76
     discussed
    0.63
     discussion
    0.61
     briefly
    0.60
     discussing
    0.57
     brief
    0.55
     examples
    0.55
     discussions
    0.54
     demonstrates
    0.53
    Activations Density 0.895%

    No Known Activations