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. 16305
    Prev
    Next
    INDEX
    Explanations

    greetings and expressions of gratitude in various forms of communication

    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
    mybatisplus
    -1.03
    WriteBarrier
    -0.93
     autorytatywna
    -0.90
     InputDecoration
    -0.87
     متعلقه
    -0.86
    хьтан
    -0.84
    Aiheesta
    -0.84
     astore
    -0.84
    migrationBuilder
    -0.83
     للمعارف
    -0.83
    POSITIVE LOGITS
     I
    0.42
     lettera
    0.39
    I
    0.39
    Greetings
    0.38
    Let
    0.36
     étn
    0.36
     berry
    0.36
     
    0.36
     råd
    0.35
     caisse
    0.33
    Activations Density 0.175%

    No Known Activations