© 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-2-9B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13157
    Prev
    Next
    INDEX
    Explanations

    specialized syntax or punctuation related to coding and programming logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.48
     faſt
    -0.45
     invokingState
    -0.43
     GetEnumerator
    -0.41
     esprits
    -0.41
     enfans
    -0.41
    Enllaces
    -0.40
    endaft
    -0.40
     Unterscheidung
    -0.40
    ều
    -0.37
    POSITIVE LOGITS
     otomatig
    0.59
     disponibilités
    0.49
    請繼續往下閱讀
    0.49
     Bourgoin
    0.46
     Raton
    0.45
    子和
    0.45
     kasarigan
    0.45
    ixi
    0.44
    avs
    0.43
    ABETH
    0.42
    Activations Density 0.207%

    No Known Activations