© 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. 8182
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical methods and analyses

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

    allowance or prevention

    np_acts-logits-general · gemini-2.0-flash

    rules, conditions, or states

    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
    Autoritní
    -0.92
     betweenstory
    -0.82
     Савезне
    -0.82
     surla
    -0.77
    WriteTagHelper
    -0.76
     Administrativna
    -0.75
    MessageTagHelper
    -0.73
    qrstuvwxyz
    -0.72
     Normdatei
    -0.70
     aDecoder
    -0.68
    POSITIVE LOGITS
     Witkin
    0.37
     means
    0.33
     itself
    0.31
     in
    0.31
     обратить
    0.29
     of
    0.29
     is
    0.29
     voet
    0.28
     även
    0.28
     appunto
    0.28
    Activations Density 1.908%

    No Known Activations