Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11873
    Prev
    Next
    INDEX
    Explanations

    terms related to theft and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.44
     poffe
    -0.43
     Reſ
    -0.40
    entingan
    -0.40
     dasarnya
    -0.38
     Relaciones
    -0.36
     Majefty
    -0.35
     gärna
    -0.35
     gratuite
    -0.34
     reaſon
    -0.34
    POSITIVE LOGITS
     theft
    1.05
     thief
    0.98
     steal
    0.98
     Theft
    0.97
     stealing
    0.96
     fraud
    0.94
     thefts
    0.94
     thieves
    0.93
     robbery
    0.91
     heist
    0.91
    Activations Density 0.349%

    No Known Activations