© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14018
    Prev
    Next
    INDEX
    Explanations

    phrases related to focus and attention

    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
     passaram
    -0.38
     possibly
    -0.37
     jonka
    -0.35
     thậm
    -0.34
     CSD
    -0.34
     citoyen
    -0.34
     suddenly
    -0.33
    orElseThrow
    -0.33
     he
    -0.32
     احتم
    -0.31
    POSITIVE LOGITS
     EconPapers
    0.61
    ArrowToggle
    0.60
    重要的是
    0.59
    的是
    0.58
     emphasizing
    0.55
    subpackage
    0.54
    VersionUID
    0.54
    xase
    0.54
     preserving
    0.53
     emphasise
    0.52
    Activations Density 0.282%

    No Known Activations