© 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. 22-GEMMASCOPE-RES-16K
    11. 10162
    Prev
    Next
    INDEX
    Explanations

    structured data and programming elements specifically related to Java and Hibernate queries

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

    Followed by ".org" or ".com"

    np_acts-logits-general · gemini-2.0-flash

    at followed by domain names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sequelize
    -0.43
    رب
    -0.43
    くい
    -0.42
    iddish
    -0.41
    CharField
    -0.41
     Golden
    -0.40
     Gel
    -0.39
     MonoBehaviour
    -0.38
     leído
    -0.38
    tehen
    -0.38
    POSITIVE LOGITS
    com
    1.36
     com
    1.33
    org
    1.09
     org
    1.06
    rungsseite
    0.90
     autorytatywna
    0.89
     pinulongan
    0.81
     nahilalakip
    0.80
    javax
    0.77
    Autoritní
    0.77
    Activations Density 0.289%

    No Known Activations