© 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. 40-GEMMASCOPE-RES-16K
    11. 5605
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "get" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    outState
    -0.46
     EdgeInsets
    -0.43
    UAGES
    -0.41
    tanleria
    -0.40
    MessageWindow
    -0.39
    intenant
    -0.39
     haberse
    -0.38
    ChildScrollView
    -0.38
    RTEE
    -0.38
    ⤹
    -0.37
    POSITIVE LOGITS
     rid
    1.38
     acquainted
    0.91
     involved
    0.87
     into
    0.84
     hold
    0.81
     stuck
    0.78
     caught
    0.77
     rewarded
    0.75
     reimbursed
    0.73
     started
    0.73
    Activations Density 0.132%

    No Known Activations