© 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. 38-GEMMASCOPE-RES-16K
    11. 8745
    Prev
    Next
    INDEX
    Explanations

    terms related to funding and financial support

    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
    ChildScrollView
    -0.37
    omitempty
    -0.35
     concentric
    -0.34
     tica
    -0.32
    iNdEx
    -0.31
    WriteAttribute
    -0.30
    berspace
    -0.30
     Hochzeit
    -0.30
     veck
    -0.29
     Vorstellungen
    -0.29
    POSITIVE LOGITS
     funding
    2.30
     grant
    2.14
     grants
    2.09
     funds
    1.99
    Funding
    1.91
    funding
    1.91
     Funding
    1.89
     Grants
    1.75
    grant
    1.74
    grants
    1.74
    Activations Density 0.697%

    No Known Activations