© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8681
    Prev
    Next
    INDEX
    Explanations

    topics related to news and current events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text appearing after certain symbols/words

    np_acts-logits-general · gemini-2.0-flash

    common words then specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     taban
    -0.42
     rígido
    -0.41
     sincerity
    -0.40
     strategi
    -0.40
    indrical
    -0.38
     modalités
    -0.37
    strategie
    -0.37
    ברית
    -0.37
    rahmen
    -0.36
     definitely
    -0.36
    POSITIVE LOGITS
     @"/
    0.81
    :✨
    0.78
    writeFieldEnd
    0.71
     lenker
    0.70
    今週
    0.70
    //
    0.70
    webElementXpaths
    0.69
    ethene
    0.69
    
    0.69
    اریخ
    0.69
    Activations Density 0.139%

    No Known Activations