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. 10066
    Prev
    Next
    INDEX
    Explanations

    phrases related to vehicle specifications and performance

    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
    malt
    -0.57
     tabaco
    -0.57
    blaze
    -0.56
    granate
    -0.54
    veil
    -0.53
    helial
    -0.53
     tobacco
    -0.51
     انس
    -0.51
     اق
    -0.50
     Hud
    -0.50
    POSITIVE LOGITS
     spring
    0.90
    Spring
    0.89
    spring
    0.88
     springs
    0.87
     Spring
    0.86
     suspension
    0.80
     Springs
    0.76
     пружи
    0.76
    springs
    0.74
     SPRING
    0.74
    Activations Density 0.177%

    No Known Activations