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. 5-GEMMASCOPE-RES-16K
    6. 11360
    Prev
    Next
    INDEX
    Explanations

    references to landscapes and their design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     @"/
    -0.94
    antMatchers
    -0.73
     amitié
    -0.73
    ഞ
    -0.72
     superstitious
    -0.71
     laiton
    -0.70
     chers
    -0.70
     tué
    -0.69
     médicale
    -0.67
     nicio
    -0.67
    POSITIVE LOGITS
     landscape
    2.15
     landscapes
    1.92
     Landscape
    1.83
    landscape
    1.78
    Landscape
    1.77
     LANDSCAPE
    1.63
     Landscapes
    1.50
     paysage
    1.36
    SCAPE
    1.34
     paisaje
    1.24
    Activations Density 0.056%

    No Known Activations