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. 2-GEMMASCOPE-RES-16K
    6. 6371
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "early" or "earliest" events or phases in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    netinet
    -0.83
    rufe
    -0.73
    ToScroll
    -0.68
     AssemblyTitle
    -0.67
    RemoveField
    -0.66
     Murdock
    -0.62
     itself
    -0.61
    tsburgh
    -0.61
     Johansson
    -0.61
     Bump
    -0.60
    POSITIVE LOGITS
     early
    4.01
    early
    3.75
    Early
    3.70
     Early
    3.67
     EARLY
    3.52
    EARLY
    3.32
     frühen
    2.54
     late
    2.26
     earliest
    2.18
     temprana
    2.17
    Activations Density 0.066%

    No Known Activations