© 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. 21-GEMMASCOPE-RES-16K
    6. 3220
    Prev
    Next
    INDEX
    Explanations

    elements related to funding or supportive actions within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tanleria
    -0.47
     ostavi
    -0.43
    قایناق‌لار
    -0.43
     Numerade
    -0.41
     regalías
    -0.41
    的问道
    -0.38
    atigable
    -0.38
    &__
    -0.38
    InitVars
    -0.37
    orice
    -0.37
    POSITIVE LOGITS
     collectively
    0.63
    全員
    0.60
    各自
    0.59
     ognuno
    0.54
     chacun
    0.54
     ciascuno
    0.53
    お互
    0.52
    กัน
    0.51
     each
    0.50
     masing
    0.48
    Activations Density 0.803%

    No Known Activations