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. 12-GEMMASCOPE-RES-16K
    6. 9981
    Prev
    Next
    INDEX
    Explanations

    instances and references to the component's state and lifecycle methods in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.68
    logii
    -0.52
     okuyayım
    -0.52
     "
    -0.52
    []{"
    -0.51
    :✨
    -0.51
    łości
    -0.51
    ToMany
    -0.51
    quelize
    -0.51
     “
    -0.50
    POSITIVE LOGITS
     StatefulWidget
    0.70
     Hopf
    0.67
    fjspx
    0.67
     esternos
    0.63
     Puig
    0.61
     StatelessWidget
    0.61
    Inver
    0.60
    QMetaType
    0.60
    SequentialGroup
    0.60
    Apellido
    0.59
    Activations Density 0.010%

    No Known Activations