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. 21-GEMMASCOPE-RES-16K
    6. 7426
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to materials, particularly metals and alloys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URLException
    -0.80
    perror
    -0.65
    ateurs
    -0.62
     كومونز
    -0.61
    MessageDigest
    -0.61
     død
    -0.60
    IBC
    -0.59
    galerie
    -0.56
    inflation
    -0.56
    SequentialGroup
    -0.55
    POSITIVE LOGITS
     grades
    0.64
     grade
    0.55
    KEYCODE
    0.52
     stel
    0.52
     steels
    0.48
    dafx
    0.47
    apimachinery
    0.46
     tremp
    0.45
     Grade
    0.45
    moveToFirst
    0.45
    Activations Density 0.222%

    No Known Activations