© 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. 7-GEMMASCOPE-RES-16K
    11. 11913
    Prev
    Next
    INDEX
    Explanations

    Java class components related to event handling and serializable objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     _
    -0.57
     Do
    -0.50
    addLast
    -0.49
     lò
    -0.48
     veneta
    -0.48
    omo
    -0.47
     Moreno
    -0.47
     slå
    -0.47
     Patel
    -0.46
    lamo
    -0.46
    POSITIVE LOGITS
    GraphicsUnit
    1.74
    BeginContext
    1.25
     EventArgs
    1.23
    EventArgs
    1.20
     createState
    1.10
    TextAppearance
    1.10
    IsContent
    1.09
     doInBackground
    1.04
    printStackTrace
    1.04
    fjspx
    0.99
    Activations Density 0.009%

    No Known Activations