© 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. 4230
    Prev
    Next
    INDEX
    Explanations

    code structure related to options and configurations

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

    Code syntax/related to code merging or combining

    np_acts-logits-general · gemini-2.0-flash

    merge or combine data structures

    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
     verlo
    -0.32
    webElement
    -0.31
    byr
    -0.26
    Members
    -0.25
    roe
    -0.24
     Hinds
    -0.24
     보기
    -0.24
    最快更新
    -0.23
    Tracce
    -0.23
     compter
    -0.23
    POSITIVE LOGITS
     merge
    1.68
     merging
    1.64
     combine
    1.63
     merged
    1.55
     combining
    1.55
     combined
    1.54
     merges
    1.51
     Combine
    1.48
     merger
    1.46
     combines
    1.45
    Activations Density 0.501%

    No Known Activations