© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 3657
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate ranking or categorization, particularly of entities associated with significance or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.57
    erape
    -0.56
     brasili
    -0.56
     granules
    -0.55
    原始内容存档
    -0.53
     ragaz
    -0.53
     biologique
    -0.53
     Tại
    -0.52
     Authenticity
    -0.52
    gisi
    -0.52
    POSITIVE LOGITS
    ViewFeatures
    1.11
    +#+#
    0.73
     &___
    0.73
    abetes
    0.71
    المشاركات
    0.70
    WithIOException
    0.69
     widely
    0.68
    /*
    0.68
    ittäin
    0.66
    ticularly
    0.66
    Activations Density 0.127%

    No Known Activations