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. 20-GEMMASCOPE-RES-16K
    6. 6808
    Prev
    Next
    INDEX
    Explanations

    quotes and dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.88
     utafitiHapana
    -0.85
    SharedCtor
    -0.79
    :✨
    -0.72
     TextInputType
    -0.71
     désolés
    -0.70
    ArrowToggle
    -0.67
     undersigned
    -0.65
     PLEASE
    -0.65
    ]")]
    -0.65
    POSITIVE LOGITS
     people
    0.81
     it
    0.76
     there
    0.76
    People
    0.74
     It
    0.74
     People
    0.68
     Leute
    0.66
     There
    0.65
     you
    0.64
     part
    0.63
    Activations Density 0.201%

    No Known Activations