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. 21-GEMMASCOPE-RES-16K
    6. 6627
    Prev
    Next
    INDEX
    Explanations

    issues related to healthcare and education systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebControls
    -0.64
    WriteAttribute
    -0.61
    +:+
    -0.60
    MENAFN
    -0.59
     AssemblyProduct
    -0.56
    msgTypes
    -0.55
     AttributeSet
    -0.54
    horabuena
    -0.53
     Lightboxes
    -0.52
     flesta
    -0.52
    POSITIVE LOGITS
     lack
    2.42
    lack
    1.86
    Lack
    1.80
     insufficient
    1.75
     Lack
    1.74
     inadequate
    1.71
     inability
    1.62
     poor
    1.58
     manque
    1.57
     falta
    1.49
    Activations Density 0.908%

    No Known Activations