© 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. 3-GEMMASCOPE-RES-16K
    11. 11263
    Prev
    Next
    INDEX
    Explanations

    mentions of contact information or details related to reaching out

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EVs
    -0.70
     ProductService
    -0.66
    glLoadIdentity
    -0.66
    یشه
    -0.64
     EDM
    -0.63
    LOYEES
    -0.63
    Streamer
    -0.62
    Hrsg
    -0.62
     rigs
    -0.61
     AppBundle
    -0.61
    POSITIVE LOGITS
     contact
    3.59
     Contact
    3.34
    contact
    3.29
    Contact
    3.21
     CONTACT
    3.10
     contacts
    2.93
    CONTACT
    2.85
     Contacts
    2.74
     contacto
    2.59
     kontak
    2.56
    Activations Density 0.044%

    No Known Activations