© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2345
    Prev
    Next
    INDEX
    Explanations

    occurrences of array and function syntaxes in the code

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

    array initialization and empty array literals in code.

    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
    setWindow
    -0.37
    versario
    -0.35
    assert
    -0.35
    这是一个
    -0.35
     devraient
    -0.35
     patrulla
    -0.35
    assertEqual
    -0.34
     setelan
    -0.34
    这是一
    -0.33
     supervivencia
    -0.33
    POSITIVE LOGITS
    Autoritní
    0.73
    astify
    0.67
     autorytatywna
    0.64
    Geplaatst
    0.61
     Roskov
    0.59
    AnchorTagHelper
    0.57
     ProtoMessage
    0.57
    出版年
    0.54
    TagMode
    0.53
     насељу
    0.53
    Activations Density 0.094%

    No Known Activations