Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 8231
    Prev
    Next
    INDEX
    Explanations

    sequences of characters or digits that represent contact information or numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mies
    -0.66
    endTime
    -0.63
    ᴇ
    -0.60
    en
    -0.60
    ε
    -0.59
     Steen
    -0.58
    ᴀ
    -0.58
    lblNewLabel
    -0.57
    ᴅ
    -0.57
    FRAGMENT
    -0.57
    POSITIVE LOGITS
    ↵↵↵↵
    2.10
    ↵↵↵↵↵↵
    1.72
    ↵↵↵↵↵↵↵↵↵↵
    1.60
    ↵↵↵↵↵↵↵↵
    1.56
    ↵↵↵↵↵↵↵
    1.45
    ↵↵↵↵↵
    1.42
    ↵↵↵↵↵↵↵↵↵↵↵↵
    1.35
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.29
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.29
    ↵↵↵↵↵↵↵↵↵↵↵
    1.28
    Activations Density 0.136%

    No Known Activations