© 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. 38-GEMMASCOPE-RES-16K
    11. 9076
    Prev
    Next
    INDEX
    Explanations

    information related to historical change and the current status of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obecnie
    -1.31
     recently
    -1.31
     currently
    -1.26
     later
    -1.23
     now
    -1.22
     eventually
    -1.22
     recientemente
    -1.20
     mittlerweile
    -1.20
     presently
    -1.20
     nowadays
    -1.20
    POSITIVE LOGITS
    IUrlHelper
    0.55
    LookAnd
    0.51
     focused
    0.49
     Савезне
    0.48
    titleMargin
    0.48
    当たり前
    0.47
    お世話
    0.47
     relied
    0.46
    FailureListener
    0.46
     focus
    0.45
    Activations Density 0.820%

    No Known Activations