© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28540
    Prev
    Next
    INDEX
    Explanations

    references to a specific software or tool called "Maltego."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words starting with Mal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.86
     quæ
    -0.85
     nakalista
    -0.84
     ſhould
    -0.84
     Clermont
    -0.83
    Inquiry
    -0.82
     itſelf
    -0.82
     Grecs
    -0.81
    ++]=
    -0.77
    océ
    -0.77
    POSITIVE LOGITS
     Mal
    1.51
     MAL
    1.46
    Mal
    1.45
     mal
    1.37
    mal
    1.29
    MAL
    1.27
     Malone
    1.18
     Maloney
    0.95
     Malden
    0.88
     Malt
    0.83
    Activations Density 0.020%

    No Known Activations