© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8110
    Prev
    Next
    INDEX
    Explanations

    technical terms related to various devices and their functionalities

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

    preceding "can" or "are"

    np_acts-logits-general · gemini-2.0-flash

    generally types of things

    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
    的就是
    -0.33
    toggler
    -0.32
    UnusedPrivate
    -0.30
     activa
    -0.30
    ご了承
    -0.29
     jo
    -0.29
     دیکھیے
    -0.29
    rungsseite
    -0.28
     Its
    -0.28
    ád
    -0.28
    POSITIVE LOGITS
     generally
    0.96
     typically
    0.88
     geralmente
    0.87
    generally
    0.84
     généralement
    0.82
     generalmente
    0.81
     umumnya
    0.81
     often
    0.79
     usually
    0.77
     zwykle
    0.73
    Activations Density 0.565%

    No Known Activations