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. 5-GEMMASCOPE-RES-16K
    6. 12601
    Prev
    Next
    INDEX
    Explanations

    references to the concept of reality

    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
    SBATCH
    -0.69
     onBind
    -0.68
    idopsis
    -0.67
    letch
    -0.66
    manship
    -0.63
     trouvera
    -0.62
    IGraphics
    -0.62
    TabIndex
    -0.62
    Alban
    -0.61
    seiti
    -0.59
    POSITIVE LOGITS
     reality
    2.24
     Reality
    2.08
    Reality
    1.98
    reality
    1.89
     realities
    1.83
     realidade
    1.44
     realidad
    1.44
     réalité
    1.35
     realty
    1.27
     realtà
    1.24
    Activations Density 0.095%

    No Known Activations