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. 18-GEMMASCOPE-RES-16K
    6. 10504
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the necessity or probability of events or actions occurring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     currently
    -0.83
    currently
    -0.78
     Currently
    -0.66
     đang
    -0.65
    Currently
    -0.63
     now
    -0.62
     CURRENT
    -0.62
     egentlig
    -0.62
    現在は
    -0.61
     actualmente
    -0.60
    POSITIVE LOGITS
     prochain
    0.88
     soon
    0.79
     demain
    0.77
     bientôt
    0.76
    DockStyle
    0.73
     Soon
    0.71
    enderror
    0.71
    Soon
    0.69
     tomorrow
    0.68
     forever
    0.68
    Activations Density 0.309%

    No Known Activations