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. 1-GEMMASCOPE-RES-16K
    6. 13445
    Prev
    Next
    INDEX
    Explanations

    words related to accessibility and ease of access

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImageBackground
    -0.72
    
    -0.69
    oneofs
    -0.68
    Xna
    -0.66
    FieldBuilder
    -0.63
    LookAnd
    -0.63
     HasFactory
    -0.62
     uVar
    -0.61
    cloudf
    -0.60
    اعمال
    -0.60
    POSITIVE LOGITS
     accessible
    4.08
     Accessible
    3.55
    accessible
    3.51
    Accessible
    3.15
     accessibility
    3.00
     accesible
    2.96
     accessibles
    2.67
     accesibles
    2.54
     inaccessible
    2.51
     Accessibility
    2.50
    Activations Density 0.073%

    No Known Activations