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. 12111
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to rights and agreements

    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
     SafeArea
    -0.43
    Received
    -0.43
    Reporter
    -0.42
    multirow
    -0.42
     osta
    -0.41
     salto
    -0.41
    Dreaming
    -0.41
     Ranked
    -0.40
    سة
    -0.39
    IComponent
    -0.39
    POSITIVE LOGITS
     explain
    1.60
     explaining
    1.59
     teach
    1.47
     explained
    1.44
     Explain
    1.41
     teaching
    1.38
    Explain
    1.31
    explain
    1.30
    Remind
    1.25
     Remind
    1.24
    Activations Density 0.608%

    No Known Activations