© 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. 3645
    Prev
    Next
    INDEX
    Explanations

    references to personal understanding and realizations

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

    followed by "now"

    np_acts-logits-general · gemini-2.0-flash

    indicating the present

    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
     الرياضيه
    -0.57
    rrggbb
    -0.53
    AsUp
    -0.52
    ſelf
    -0.48
    XmlAccessorType
    -0.48
    ThroughAttribute
    -0.47
    ServletException
    -0.47
     bParam
    -0.46
    RegistryLite
    -0.44
    styleType
    -0.44
    POSITIVE LOGITS
     now
    3.13
     ahora
    2.36
    now
    2.28
     теперь
    2.17
     maintenant
    2.17
     sekarang
    2.16
     nyní
    2.03
     agora
    1.98
     teraz
    1.94
     Now
    1.91
    Activations Density 0.618%

    No Known Activations