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. 13-GEMMASCOPE-RES-16K
    6. 15233
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "is" and variations of "to be" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -1.01
    #
    -1.00
     Meksiku
    -0.91
    TagMode
    -0.90
     kaarangay
    -0.89
    AutoScaleMode
    -0.82
    HostException
    -0.81
     paar
    -0.81
    antMatchers
    -0.80
    Sucesor
    -0.79
    POSITIVE LOGITS
     مید
    0.69
     stuff
    0.68
    σία
    0.66
    Cuál
    0.65
     neuem
    0.65
     oreilles
    0.65
     something
    0.63
     legislation
    0.60
     weevil
    0.60
     člov
    0.60
    Activations Density 0.168%

    No Known Activations