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. 20-GEMMASCOPE-RES-16K
    6. 6406
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantities or assessments related to significance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelAdmin
    -0.68
     صوتيه
    -0.59
     instructions
    -0.58
     المعيارى
    -0.57
     instruction
    -0.57
     negroes
    -0.57
     savages
    -0.56
    บัติ
    -0.56
     petals
    -0.55
     يتيمه
    -0.54
    POSITIVE LOGITS
     variety
    0.66
     Vielzahl
    0.63
     myriad
    0.63
     multitude
    0.59
     greater
    0.59
     plethora
    0.58
     range
    0.56
    PerformLayout
    0.56
     broad
    0.55
     sense
    0.55
    Activations Density 0.634%

    No Known Activations