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. 12262
    Prev
    Next
    INDEX
    Explanations

    terms related to electronic properties and valence states of elements, particularly europium in various compounds and alloys

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

    Chemical elements and compounds

    np_acts-logits-general · gemini-2.0-flash

    Europium alloys and materials

    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
    Membrane
    -0.60
    AndroidJUnit
    -0.55
     endwhile
    -0.54
     nene
    -0.54
    LabelTagHelper
    -0.51
     HasFactory
    -0.49
     Membrane
    -0.49
    geslacht
    -0.48
     Plast
    -0.48
     StatefulWidget
    -0.48
    POSITIVE LOGITS
     alloy
    0.76
    alloy
    0.65
     alloys
    0.64
     metallurgy
    0.62
    yntaxException
    0.62
     Alloys
    0.59
    \{\\
    0.59
     Alloy
    0.59
     Winaray
    0.58
     NavController
    0.58
    Activations Density 1.233%

    No Known Activations