© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6001
    Prev
    Next
    INDEX
    Explanations

    references to specific file systems or frameworks related to programming, particularly involving "Fi"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.60
     feroit
    -0.56
    ReusableCell
    -0.56
     المعيارى
    -0.55
    expandindo
    -0.54
    әрмәләр
    -0.53
    енча
    -0.53
    сылкі
    -0.52
    retweeted
    -0.51
    FieldOffsetTable
    -0.50
    POSITIVE LOGITS
     fi
    2.33
     Fi
    2.25
    Fi
    2.13
    fi
    2.08
     FI
    1.88
    FI
    1.82
     фи
    1.70
    フィ
    1.48
     fic
    1.43
     Фи
    1.41
    Activations Density 1.093%

    No Known Activations