© 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. 8024
    Prev
    Next
    INDEX
    Explanations

    references to medical studies or research findings related to health and treatment outcomes

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

    Citations/references (e.g., ^[@ref135]^)

    np_acts-logits-general · gemini-2.0-flash

    citation and reference markers

    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
     always
    -0.69
     never
    -0.60
    always
    -0.52
    Always
    -0.51
     всегда
    -0.51
     Always
    -0.49
     sempre
    -0.48
     siempre
    -0.48
     תמיד
    -0.48
     alltid
    -0.47
    POSITIVE LOGITS
    KommentareTeilen
    0.59
     kasarigan
    0.58
     ویکی‌آمباردا
    0.55
    Viungo
    0.54
    thâu
    0.54
    Personensuche
    0.53
     createSprite
    0.51
    🔕
    0.50
     Hygien
    0.50
    GenerationType
    0.50
    Activations Density 0.739%

    No Known Activations