© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3030
    Prev
    Next
    INDEX
    Explanations

    references to code elements and their implementation in programming contexts

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

    Android-related code and layouts

    np_acts-logits-general · gemini-2.0-flash

    android common UI components

    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
    鼠标
    -0.58
     nahilalakip
    -0.57
    IUrlHelper
    -0.56
    closePath
    -0.54
    Portale
    -0.54
    multer
    -0.50
     scolaire
    -0.50
     Sequelize
    -0.48
    alegal
    -0.48
    quelize
    -0.48
    POSITIVE LOGITS
     android
    0.93
     Android
    0.87
     activity
    0.86
    Activity
    0.84
     Activity
    0.83
    activity
    0.83
    android
    0.82
    Android
    0.76
    ctivity
    0.72
    Toast
    0.69
    Activations Density 0.744%

    No Known Activations