© 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. 7-GEMMASCOPE-RES-16K
    11. 6605
    Prev
    Next
    INDEX
    Explanations

    terms related to financial expenditures and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndInit
    -0.61
    iddhar
    -0.60
    olesale
    -0.58
    mphony
    -0.58
     Barna
    -0.58
     мәкал
    -0.57
     ostavi
    -0.57
    ichy
    -0.57
    astronomie
    -0.56
     Efq
    -0.56
    POSITIVE LOGITS
     depreciation
    0.64
     depre
    0.62
     maintenance
    0.57
     buil
    0.53
    setContentView
    0.53
    depre
    0.53
     equipment
    0.52
     OFDb
    0.51
     refurb
    0.50
    rungsseite
    0.50
    Activations Density 0.223%

    No Known Activations