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. 6764
    Prev
    Next
    INDEX
    Explanations

    specific scientific measurements and quantities related to experimental results

    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
    ViewFeatures
    -0.64
    WebVitals
    -0.61
    esez
    -0.58
     BoxDecoration
    -0.57
    ometra
    -0.57
    wydd
    -0.57
    достатки
    -0.55
    \{\\
    -0.55
    ције
    -0.54
    UnsafeEnabled
    -0.54
    POSITIVE LOGITS
    rpm
    0.57
     words
    0.53
     rpm
    0.53
    px
    0.52
    dpi
    0.51
     yards
    0.47
     RPM
    0.47
     pixels
    0.47
    vų
    0.47
     mAh
    0.47
    Activations Density 0.750%

    No Known Activations