© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 873
    Prev
    Next
    INDEX
    Explanations

    references to various types of models in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Model" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    model types and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.81
    IBarButtonItem
    -0.77
     BoxFit
    -0.73
    waitKey
    -0.68
     дописавши
    -0.67
    <!--[
    -0.67
    fjspx
    -0.66
     otomatig
    -0.65
    RouterModule
    -0.64
    CardHeader
    -0.64
    POSITIVE LOGITS
     models
    0.95
     MODEL
    0.95
    Models
    0.92
     Models
    0.90
     Model
    0.84
     MODELS
    0.84
    models
    0.83
    MODEL
    0.79
     model
    0.78
     模型
    0.77
    Activations Density 0.122%

    No Known Activations