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. 16-GEMMASCOPE-RES-16K
    6. 3007
    Prev
    Next
    INDEX
    Explanations

    mechanical devices and their functionalities

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

    phones or phone functions

    np_acts-logits-general · gemini-2.0-flash

    phone ringtone activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CGI
    -0.52
     ojo
    -0.50
    WebElementEntity
    -0.50
    Slf
    -0.45
    CGI
    -0.45
    setVerticalGroup
    -0.44
    gisi
    -0.43
    sauce
    -0.43
     erklä
    -0.43
    ว์
    -0.43
    POSITIVE LOGITS
     phone
    0.83
     المعيارى
    0.78
     handleMessage
    0.70
     telefon
    0.68
     ringtones
    0.68
     initComponents
    0.67
     Phone
    0.66
     phones
    0.66
     ringtone
    0.66
    Phone
    0.65
    Activations Density 0.316%

    No Known Activations