© 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. 0-GEMMASCOPE-RES-16K
    11. 9103
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     activer
    -0.40
    arschijnlijk
    -0.36
     blad
    -0.35
     brou
    -0.35
     convenable
    -0.35
    UrlResolution
    -0.35
    skap
    -0.33
    ᵎ
    -0.33
     tremp
    -0.33
     pokok
    -0.33
    POSITIVE LOGITS
    
    0.59
     Enclosed
    0.54
     voluto
    0.54
    charge
    0.54
    Charge
    0.53
    Charges
    0.53
    charges
    0.53
     Charges
    0.51
    Pon
    0.50
     enclosed
    0.50
    Activations Density 1.916%

    No Known Activations