Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 5779
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of places and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.86
    .*")]
    -0.83
    ValueGeneration
    -0.79
     الرياضيه
    -0.78
    цезда
    -0.73
    BeginContext
    -0.73
     protoimpl
    -0.72
     ExecuteAsync
    -0.71
     gainera
    -0.71
     الحره
    -0.71
    POSITIVE LOGITS
    الحياه
    0.46
    ,
    0.44
     morts
    0.43
     ITIS
    0.42
    人和
    0.41
    tagHelperRunner
    0.40
     glatt
    0.39
    PrototypeOf
    0.39
    קישורים
    0.39
     casó
    0.39
    Activations Density 1.261%

    No Known Activations