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. 19-GEMMASCOPE-RES-16K
    6. 2311
    Prev
    Next
    INDEX
    Explanations

    references 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-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteBarrier
    -0.79
    DeleteBehavior
    -0.66
    GraphicsUnit
    -0.65
     FontWeight
    -0.64
    ControllerAdvice
    -0.62
    ouwd
    -0.61
    Obrázky
    -0.59
    ogast
    -0.57
     CommandType
    -0.56
     Barbuda
    -0.54
    POSITIVE LOGITS
     funding
    2.26
    Funding
    1.87
    funding
    1.84
     Funding
    1.83
     financing
    1.83
     funded
    1.60
     funders
    1.60
     funds
    1.59
     financement
    1.54
     fund
    1.45
    Activations Density 0.311%

    No Known Activations