© 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. 36-GEMMASCOPE-RES-16K
    11. 16222
    Prev
    Next
    INDEX
    Explanations

    phrases that denote attention and concentration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.60
     kasarigan
    -0.56
     ControllerBase
    -0.52
    KommentareTeilen
    -0.51
    EIF
    -0.49
     CURIAM
    -0.49
    RTSN
    -0.47
     виправивши
    -0.47
    LookAnd
    -0.47
    PYX
    -0.46
    POSITIVE LOGITS
     attention
    0.82
    Attention
    0.73
    attention
    0.66
     Attention
    0.66
     внимания
    0.64
     efforts
    0.62
     attentions
    0.60
     atención
    0.59
     effort
    0.59
     ATTENTION
    0.56
    Activations Density 0.128%

    No Known Activations