© 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. 14496
    Prev
    Next
    INDEX
    Explanations

    the presence of distinct input markers or signaling elements in a document

    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
    RegressionTest
    -0.60
    richTextPanel
    -0.53
    zęd
    -0.49
    ffindor
    -0.49
    CLAIMER
    -0.48
    guard
    -0.46
     pleaſure
    -0.45
    dani
    -0.45
     protes
    -0.45
    емость
    -0.44
    POSITIVE LOGITS
     propOrder
    0.64
    /**
    0.57
    complexContent
    0.57
     geg
    0.54
    gapi
    0.52
     Referential
    0.51
    alleri
    0.51
     aikaa
    0.49
    ########.
    0.48
    kezik
    0.47
    Activations Density 0.185%

    No Known Activations