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. 10618
    Prev
    Next
    INDEX
    Explanations

    references to keys or critical elements necessary for understanding or achieving something significant

    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
    θεια
    -0.58
     lipid
    -0.50
     Reborn
    -0.49
     romain
    -0.48
    levy
    -0.47
    hyrchwyd
    -0.46
    oult
    -0.45
    Thin
    -0.45
    Filmografia
    -0.45
     صدر
    -0.45
    POSITIVE LOGITS
     keys
    1.96
     Keys
    1.72
     KEYS
    1.58
     key
    1.58
    keys
    1.45
     Key
    1.44
    Keys
    1.41
     Schlüssel
    1.39
     KEY
    1.34
    🔑
    1.33
    Activations Density 0.140%

    No Known Activations