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. 12076
    Prev
    Next
    INDEX
    Explanations

    occurrences of functions related to handling events and actions

    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
     betweenstory
    -0.82
    śród
    -0.76
    ByDefault
    -0.75
     minY
    -0.66
     strerror
    -0.65
     때문
    -0.62
    uksessa
    -0.61
     onResume
    -0.61
     acaso
    -0.61
     recyclerView
    -0.60
    POSITIVE LOGITS
    handle
    2.98
     handle
    2.82
     Handle
    2.82
    Handle
    2.80
     HANDLE
    2.55
     handles
    2.51
    handles
    2.46
     Handles
    2.45
    HANDLE
    2.31
    Handles
    2.19
    Activations Density 0.042%

    No Known Activations