© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11606
    Prev
    Next
    INDEX
    Explanations

    data structures and their corresponding code representations

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

    hexadecimal numbers and coordinate values in structured data or 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
     متعلقه
    -0.59
     tranſ
    -0.53
     Jefus
    -0.53
     myſelf
    -0.51
     typique
    -0.50
     anſ
    -0.50
     poffible
    -0.49
     meille
    -0.49
     Inscrivez
    -0.48
     leaſt
    -0.47
    POSITIVE LOGITS
     InputDecoration
    0.49
    CppMethod
    0.49
    хьтан
    0.45
    цездатний
    0.40
     nonUne
    0.40
    planta
    0.39
    makeConstraints
    0.39
    SequentialGroup
    0.39
     hex
    0.39
    sidemargin
    0.38
    Activations Density 2.239%

    No Known Activations