© 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. 33-GEMMASCOPE-RES-16K
    11. 11550
    Prev
    Next
    INDEX
    Explanations

    elements related to legal arguments and liabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.71
    PerformLayout
    -0.60
     Signalez
    -0.59
     Exactos
    -0.58
    Tikang
    -0.58
    Jîn
    -0.57
    SourceChecksum
    -0.56
    findpost
    -0.54
    تقاوى
    -0.50
    Personendaten
    -0.48
    POSITIVE LOGITS
     let
    2.27
    let
    1.64
     much
    1.52
     Let
    1.51
    Let
    1.49
    much
    1.35
     LET
    1.35
    Much
    1.31
     Much
    1.21
    LET
    1.16
    Activations Density 0.282%

    No Known Activations