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. 6-GEMMASCOPE-RES-16K
    6. 5324
    Prev
    Next
    INDEX
    Explanations

    instances of the word "maybe."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >--}}
    -0.91
     Hirsch
    -0.88
    "));
    
    -0.86
    )));
    
    -0.84
    лян
    -0.81
    ς
    -0.81
     saites
    -0.78
     listView
    -0.78
    geist
    -0.78
    )”
    -0.77
    POSITIVE LOGITS
    CreateMap
    0.83
     Brend
    0.80
     Mow
    0.78
     Xan
    0.76
     Gae
    0.76
     Mep
    0.73
    Decre
    0.72
    malink
    0.72
     Preg
    0.72
    chaik
    0.72
    Activations Density 0.118%

    No Known Activations