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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 7344
    Prev
    Next
    INDEX
    Explanations

    instances of theft, burglary, and related criminal activities

    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
    ########.
    -0.57
    Risultati
    -0.47
    tagext
    -0.46
     Walkover
    -0.45
     سكانية
    -0.45
     referrerpolicy
    -0.45
    OGND
    -0.44
    SourceChecksum
    -0.44
    StoreMessageInfo
    -0.44
     puol
    -0.43
    POSITIVE LOGITS
     theft
    1.39
     Theft
    1.27
     steal
    1.27
     stealing
    1.24
     stolen
    1.23
    theft
    1.23
     thefts
    1.22
    Theft
    1.21
     steals
    1.17
     stole
    1.16
    Activations Density 0.307%

    No Known Activations