© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4495
    Prev
    Next
    INDEX
    Explanations

    references to plea bargaining and legal exchanges involving immunity or reduced sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Assess
    -0.53
    Assess
    -0.52
     utafitiHapana
    -0.50
     ost
    -0.48
    alib
    -0.47
     Philip
    -0.47
     swan
    -0.47
     المعيارى
    -0.46
     Gak
    -0.46
     Dag
    -0.45
    POSITIVE LOGITS
     Vereinbarung
    0.48
     promesse
    0.47
    RUnlock
    0.47
    rrggbb
    0.44
     promete
    0.42
     promesas
    0.41
     promesa
    0.39
     Forderung
    0.38
     promise
    0.37
    Promise
    0.37
    Activations Density 0.656%

    No Known Activations