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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 1770
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to electrical circuits and components

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

    Winding or phase associated with motors or inverters

    np_acts-logits-general · gemini-2.0-flash

    electrical phases and inverter components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     radio
    -0.48
     []:
    -0.47
     memorial
    -0.47
     Guil
    -0.43
     Radio
    -0.43
     biz
    -0.42
     RNG
    -0.42
    Radio
    -0.41
    radio
    -0.41
     RADIO
    -0.40
    POSITIVE LOGITS
    ">//
    0.92
    mybatisplus
    0.87
    rungsseite
    0.86
     GenerationType
    0.84
    GEBURTSDATUM
    0.79
    ⓧ
    0.76
    OGND
    0.73
    المناصب
    0.70
    principalColumn
    0.70
    encodeWith
    0.67
    Activations Density 0.344%

    No Known Activations