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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2397
    Prev
    Next
    INDEX
    Explanations

    references to apocalyptic themes and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @[+][
    -0.70
     المعيارى
    -0.58
    OrBuilder
    -0.56
     AspNetCore
    -0.55
    __':
    -0.53
     Vikipedi
    -0.52
     hinein
    -0.51
     kea
    -0.50
    avigation
    -0.50
     vettoriale
    -0.48
    POSITIVE LOGITS
     apocalypse
    0.82
    Apocalypse
    0.79
    apture
    0.77
     Apocalypse
    0.72
    PMailer
    0.68
    sunami
    0.67
    geddon
    0.66
    omsday
    0.65
     Armageddon
    0.64
     doom
    0.62
    Activations Density 0.486%

    No Known Activations