© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7882
    Prev
    Next
    INDEX
    Explanations

    financial terms related to loans and debit cards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.80
     nakalista
    -0.74
    addContainerGap
    -0.63
     فريبيس
    -0.60
     ब्रेकडाउन
    -0.59
     Wicidata
    -0.57
    arangay
    -0.57
     conmigo
    -0.54
     Efq
    -0.53
    tanleria
    -0.51
    POSITIVE LOGITS
     Equip
    0.40
     bicarbon
    0.40
     Poss
    0.40
    Avail
    0.39
    Equip
    0.39
     koch
    0.39
    Hence
    0.39
    Poss
    0.38
    condition
    0.38
     Hence
    0.37
    Activations Density 0.120%

    No Known Activations