© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 15445
    Prev
    Next
    INDEX
    Explanations

    references related to payments or financial transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.40
    oneofs
    -0.40
     GoogleFonts
    -0.38
    ChildScrollView
    -0.38
    artz
    -0.37
     Baillargeon
    -0.36
    исленность
    -0.36
    Carriera
    -0.36
     Италијани
    -0.35
    ⤹
    -0.35
    POSITIVE LOGITS
     full
    4.09
     Full
    3.47
    full
    3.34
     FULL
    3.28
    Full
    3.16
    FULL
    2.89
     peł
    2.63
    フル
    2.52
     penuh
    2.45
     fuller
    2.33
    Activations Density 1.620%

    No Known Activations