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. 14404
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences involving expressions of affection or friendship

    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
    smithy
    -0.57
    ApiModel
    -0.55
     Roskov
    -0.48
    baix
    -0.48
     Mangel
    -0.47
    unteer
    -0.47
    CppMethod
    -0.45
    دانشنامهٔ
    -0.45
     Egli
    -0.45
    mybatisplus
    -0.44
    POSITIVE LOGITS
     thank
    1.69
     thanking
    1.57
     goodbye
    1.48
     Thank
    1.45
     greetings
    1.42
     THANK
    1.39
     thanked
    1.38
    thank
    1.37
     hello
    1.35
     greeting
    1.33
    Activations Density 0.224%

    No Known Activations