© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 11490
    Prev
    Next
    INDEX
    Explanations

    references to extending or expanding concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMailer
    -1.04
     Nj
    -0.85
    bootstrapcdn
    -0.84
     ModelExpression
    -0.83
     وتسجيلات
    -0.82
     للمعارف
    -0.82
    queryInterface
    -0.81
     HasFactory
    -0.81
     CreateTagHelper
    -0.80
    èdia
    -0.80
    POSITIVE LOGITS
     extended
    1.94
    Extended
    1.76
     extend
    1.76
     Extended
    1.74
     Extend
    1.72
    extended
    1.70
    Extend
    1.69
     extending
    1.66
     extension
    1.59
     extends
    1.55
    Activations Density 0.106%

    No Known Activations