Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 1770
    Prev
    Next
    INDEX
    Explanations

    words related to development and creation of methodologies or models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nargin
    -0.65
    issances
    -0.62
    SuppressMessage
    -0.61
     remercie
    -0.59
     onPostExecute
    -0.55
     remercier
    -0.54
     doInBackground
    -0.54
     vectorielle
    -0.54
     dentaire
    -0.54
     considér
    -0.53
    POSITIVE LOGITS
     Chwiliwch
    0.86
     create
    0.85
     creating
    0.83
     Create
    0.83
    VIAF
    0.81
    Creating
    0.79
     vytvoř
    0.79
    creating
    0.78
     new
    0.77
     a
    0.77
    Activations Density 0.391%

    No Known Activations