© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11571
    Prev
    Next
    INDEX
    Explanations

    references to crime or criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aner
    -0.52
    ...');
    -0.49
    。
    -0.46
    в
    -0.46
     alkohol
    -0.46
    、「
    -0.44
    「
    -0.44
    кон
    -0.44
    。「
    -0.44
     plak
    -0.43
    POSITIVE LOGITS
    WriteBarrier
    0.89
     وتسجيلات
    0.84
    CPtr
    0.81
    awtextra
    0.76
     utafitiHapana
    0.75
    LookAnd
    0.74
     BoxDecoration
    0.71
     متعلقه
    0.70
    æder
    0.69
    VIAF
    0.68
    Activations Density 0.554%

    No Known Activations