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. 16074
    Prev
    Next
    INDEX
    Explanations

    repeated use of the term "pattern" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of a “pattern” in technical or scientific contexts, often including its properties or relations (e.g., “pattern of/in/is/within”).

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    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
    PerformLayout
    -0.93
    CURLOPT
    -0.89
     íntimo
    -0.85
    DotNetBar
    -0.82
    IsPostBack
    -0.77
     CURLOPT
    -0.77
    ixeira
    -0.76
    RemoteException
    -0.73
    Wikis
    -0.71
     biotite
    -0.71
    POSITIVE LOGITS
     pattern
    3.54
     patterns
    3.41
     Pattern
    3.27
     Patterns
    3.18
    pattern
    3.10
     PATTERN
    3.09
    Pattern
    3.04
    Patterns
    2.95
    patterns
    2.79
    PATTERN
    2.43
    Activations Density 0.064%

    No Known Activations