© 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. 11-GEMMASCOPE-RES-16K
    11. 1620
    Prev
    Next
    INDEX
    Explanations

    terms related to theft, robbery, and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
    Portály
    -0.69
    tonode
    -0.67
     myſelf
    -0.64
    lamy
    -0.59
    nourriture
    -0.58
     umbi
    -0.57
     hautes
    -0.57
     itſelf
    -0.56
     TestBed
    -0.56
    شهاد
    -0.56
    POSITIVE LOGITS
     theft
    1.20
     thefts
    1.12
     steals
    1.11
     stolen
    1.10
     steal
    1.05
     stole
    1.04
     thieves
    1.02
    theft
    1.01
     robbed
    1.00
     robbery
    0.99
    Activations Density 0.199%

    No Known Activations