© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4391
    Prev
    Next
    INDEX
    Explanations

    financial metrics and verification processes related to revenue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    struts
    -0.89
    expandindo
    -0.87
    parsedMessage
    -0.85
    o
    -0.82
    ISupport
    -0.81
    IBOutlet
    -0.80
     Sunderland
    -0.79
     Soll
    -0.79
    classnames
    -0.78
     ostr
    -0.77
    POSITIVE LOGITS
    uesday
    0.81
     Wex
    0.72
     spalle
    0.70
    anxiety
    0.66
     kefir
    0.64
    řez
    0.64
    Grief
    0.64
     ename
    0.63
    jegy
    0.63
    PageContext
    0.62
    Activations Density 0.125%

    No Known Activations