© 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. 31-GEMMASCOPE-RES-16K
    11. 3421
    Prev
    Next
    INDEX
    Explanations

    references to the term "flat" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "flat" as a standalone term or adjective.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Derbyniad
    -0.52
    Viited
    -0.45
    oredCriteria
    -0.43
     VIDEOTAPE
    -0.40
    存于互联网档案馆
    -0.39
    LogError
    -0.38
     CiNii
    -0.37
    Legături
    -0.36
    RefNanny
    -0.36
    Kirchen
    -0.34
    POSITIVE LOGITS
     Flat
    0.97
    Flat
    0.94
     FLAT
    0.93
     flat
    0.93
    flat
    0.88
    FLAT
    0.84
     flatten
    0.73
     flattening
    0.71
     flattened
    0.69
     flatter
    0.66
    Activations Density 0.082%

    No Known Activations