© 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. 39-GEMMASCOPE-RES-16K
    11. 4516
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the whitespace character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.96
     ब्रेकडाउन
    -0.95
    tagHelperRunner
    -0.94
    RegressionTest
    -0.94
    AndEndTag
    -0.89
     utafitiHapana
    -0.88
    TagMode
    -0.87
     Numerade
    -0.86
    ConstraintMaker
    -0.83
    AddTagHelper
    -0.82
    POSITIVE LOGITS
     Masyarakat
    0.40
    等
    0.35
     
    0.34
    当
    0.32
     Nusantara
    0.32
    偏
    0.31
    接待
    0.30
    先
    0.29
     Organisations
    0.29
    美
    0.29
    Activations Density 0.062%

    No Known Activations