© 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. 2526
    Prev
    Next
    INDEX
    Explanations

    references to specific types of vehicles and their features

    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
    AndEndTag
    -0.74
    يكب
    -0.52
     producers
    -0.51
    ISOString
    -0.48
    bcryptjs
    -0.48
     tôt
    -0.48
     salespeople
    -0.48
     Producers
    -0.47
     Producer
    -0.47
     Ricci
    -0.47
    POSITIVE LOGITS
     build
    1.00
     fabrication
    0.95
     Fabrication
    0.94
    build
    0.90
     building
    0.90
     builds
    0.87
    Fabrication
    0.85
     Build
    0.84
    building
    0.83
    Building
    0.82
    Activations Density 0.239%

    No Known Activations