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. 12-GEMMASCOPE-RES-16K
    6. 109
    Prev
    Next
    INDEX
    Explanations

    assertions and discussions about the concept of truth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollectionView
    -0.74
     '{@
    -0.73
     通販
    -0.72
     Garvey
    -0.71
     Berikut
    -0.71
    RegistryLite
    -0.68
    addPreferredGap
    -0.67
     følgende
    -0.65
    DockStyle
    -0.64
    Décès
    -0.64
    POSITIVE LOGITS
     truth
    1.38
     truths
    1.35
     Truth
    1.32
     TRUTH
    1.29
     Truths
    1.25
    truth
    1.23
    Truth
    1.08
     lies
    0.94
     facts
    0.93
     lie
    0.87
    Activations Density 0.104%

    No Known Activations