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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 10104
    Prev
    Next
    INDEX
    Explanations

    references to social gatherings or communal experiences

    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
     nakalista
    -0.76
     vœux
    -0.67
    seamnă
    -0.64
    __(/*!
    -0.63
     preuves
    -0.62
    ніципалі
    -0.62
     contactez
    -0.60
    setVerticalGroup
    -0.57
     rêves
    -0.56
     lenker
    -0.56
    POSITIVE LOGITS
     passers
    1.27
     tourists
    1.17
     visitors
    1.13
     people
    1.06
     passer
    0.95
     Tourists
    0.94
     pedestrians
    0.91
    people
    0.89
     traffic
    0.88
    Visitors
    0.87
    Activations Density 0.240%

    No Known Activations