© 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. 7179
    Prev
    Next
    INDEX
    Explanations

    concepts related to health and disease management

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

    before prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    comparison and contrast

    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
    saraba
    -0.56
    forChild
    -0.51
    /*++
    -0.47
    Даже
    -0.45
     LEYENDO
    -0.45
    UnusedPrivate
    -0.45
    ########.
    -0.44
     Nhưng
    -0.44
    ailleurs
    -0.43
    그러나
    -0.43
    POSITIVE LOGITS
     versus
    0.64
     anhand
    0.58
     vs
    0.58
     contrasted
    0.53
     Hinblick
    0.52
     específicamente
    0.50
     compared
    0.50
     implications
    0.50
     perspectiva
    0.48
     khususnya
    0.47
    Activations Density 0.790%

    No Known Activations