Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3372
    Prev
    Next
    INDEX
    Explanations

    references to effectiveness in marketing and advertising strategies

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

    car detailing and cleaning

    np_acts-logits-general · gemini-2.0-flash

    wax and detail

    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
    Tembelea
    -0.62
     <",
    -0.55
     Ministério
    -0.52
     Umbau
    -0.50
    はじめに
    -0.50
     levis
    -0.49
     scom
    -0.48
    openzeppelin
    -0.48
     Kessel
    -0.47
     hippocampus
    -0.47
    POSITIVE LOGITS
     Detail
    1.07
    detail
    1.05
     detailing
    0.96
     detail
    0.96
    Detail
    0.93
     DETAIL
    0.90
     wax
    0.89
     Wax
    0.82
    Wax
    0.81
    wax
    0.78
    Activations Density 0.104%

    No Known Activations