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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-GEMMASCOPE-RES-16K
    6. 1902
    Prev
    Next
    INDEX
    Explanations

    clinical trial terminology and references

    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
     كومونز
    -0.73
     bee
    -0.56
    rensa
    -0.54
     getItemId
    -0.53
    bee
    -0.52
     soucis
    -0.52
     désactiv
    -0.51
     Indust
    -0.51
    ReusableCell
    -0.51
    withOpacity
    -0.51
    POSITIVE LOGITS
    WithIOException
    0.78
     trials
    0.71
     trial
    0.64
    Trials
    0.64
     randomized
    0.59
     Trials
    0.58
     conducted
    0.57
     experiment
    0.56
     betweenstory
    0.56
     experiments
    0.55
    Activations Density 1.271%

    No Known Activations