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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 3932
    Prev
    Next
    INDEX
    Explanations

    references to environmental remediation and pollution management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.44
    (!__
    -0.41
     gebeten
    -0.40
    /**
    -0.39
    LookAnd
    -0.38
     Squash
    -0.37
    ngdoc
    -0.37
     podró
    -0.37
    fficiency
    -0.36
     trụ
    -0.36
    POSITIVE LOGITS
     remediation
    1.00
     contaminated
    1.00
     cleanup
    0.89
     remedi
    0.88
     contamination
    0.87
     Remediation
    0.84
    contaminated
    0.84
     decontamination
    0.81
     contaminant
    0.79
    Conta
    0.79
    Activations Density 0.254%

    No Known Activations