Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13595
    Prev
    Next
    INDEX
    Explanations

    financial terms and concepts related to contracts and rental agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Reference to a rate or calculation

    np_acts-logits-general · gemini-2.0-flash

    rate and calculation of monetary values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     preocupar
    -0.49
    צת
    -0.47
     hum
    -0.42
     RSVP
    -0.41
     Investi
    -0.40
     конф
    -0.39
     nerede
    -0.39
     organized
    -0.38
    хим
    -0.38
     MOT
    -0.37
    POSITIVE LOGITS
     formula
    0.96
     calculation
    0.96
    justed
    0.90
    kháu
    0.89
     adjustments
    0.85
     adjusted
    0.84
     adjustment
    0.84
    calculation
    0.83
    formula
    0.81
     Calculation
    0.80
    Activations Density 0.584%

    No Known Activations