© 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. 25-GEMMASCOPE-RES-16K
    11. 7603
    Prev
    Next
    INDEX
    Explanations

    mentions of security and surveillance in community contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.67
    RUnlock
    -0.56
    ModelBuilder
    -0.56
    leges
    -0.52
    Portail
    -0.50
     OFDb
    -0.50
    marginHorizontal
    -0.49
     TextInputType
    -0.49
    addCriterion
    -0.48
    XMLSchema
    -0.48
    POSITIVE LOGITS
     round
    1.38
    round
    1.14
     day
    1.09
     seven
    1.09
     Round
    1.05
     twenty
    1.04
    Round
    1.02
     ROUND
    1.02
     night
    0.99
    ROUND
    0.94
    Activations Density 0.261%

    No Known Activations