© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 16047
    Prev
    Next
    INDEX
    Explanations

    terms related to legal concepts, specifically fraud

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -1.21
    ftagPool
    -0.96
    WriteTagHelper
    -0.95
    ]")]
    -0.89
    setVerticalGroup
    -0.86
    TagMode
    -0.85
    XmlAccessType
    -0.84
    bootstrapcdn
    -0.82
    richTextPanel
    -0.81
    IsContent
    -0.80
    POSITIVE LOGITS
     iD
    0.53
     photolibrary
    0.49
     fú
    0.48
     MIA
    0.48
     adjourned
    0.47
     TOE
    0.46
     unifor
    0.46
     Mauricio
    0.46
     puer
    0.45
     ECR
    0.45
    Activations Density 0.326%

    No Known Activations