© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8931
    Prev
    Next
    INDEX
    Explanations

    verbs related to the formal processes or actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    genodigd
    -0.47
     sempat
    -0.47
    ükemmel
    -0.46
    makeConstraints
    -0.45
     Paglinawan
    -0.45
    pulseira
    -0.43
     WaitForSeconds
    -0.43
     belangrij
    -0.43
    MigrationBuilder
    -0.43
    indelijk
    -0.42
    POSITIVE LOGITS
    存于互联网档案馆
    0.59
     occur
    0.57
     kasarigan
    0.57
     occurs
    0.53
     exist
    0.48
    Personendaten
    0.48
    MathML
    0.47
    といけない
    0.46
     exists
    0.45
    RTLD
    0.43
    Activations Density 0.353%

    No Known Activations