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. 0-GEMMASCOPE-RES-16K
    6. 6364
    Prev
    Next
    INDEX
    Explanations

    the word "here"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    typeof
    -0.69
     thước
    -0.56
    )");
    
    -0.56
     mola
    -0.55
    ubus
    -0.55
    Westfalen
    -0.54
     multic
    -0.54
     difp
    -0.53
    loài
    -0.53
    rosia
    -0.52
    POSITIVE LOGITS
     here
    4.80
    here
    3.90
     Here
    3.69
     aquí
    3.54
     HERE
    3.49
    Here
    3.47
    HERE
    3.21
     aqui
    3.19
     ici
    3.10
     здесь
    3.06
    Activations Density 0.065%

    No Known Activations