© 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. 24-GEMMASCOPE-RES-16K
    11. 2610
    Prev
    Next
    INDEX
    Explanations

    references to email communication and contact information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Email addresses and contact information

    np_acts-logits-general · gemini-2.0-flash

    email addresses and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nemlig
    -0.61
    RTDA
    -0.59
     totiž
    -0.58
     opérateur
    -0.56
     DbType
    -0.55
    互联网档案馆
    -0.55
     bowiem
    -0.54
    Дереккөздер
    -0.52
     namelijk
    -0.51
    HttpException
    -0.51
    POSITIVE LOGITS
     info
    1.30
    info
    1.04
     Info
    0.97
     INFO
    0.88
     Email
    0.85
     Contact
    0.81
    contact
    0.81
     email
    0.80
    Email
    0.80
     contact
    0.79
    Activations Density 0.086%

    No Known Activations