Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5775
    Prev
    Next
    INDEX
    Explanations

    terms and definitions related to mathematical functions and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppCodeGen
    -0.42
    #+#
    -0.40
    ритори
    -0.36
    ubern
    -0.36
    muth
    -0.35
    IContainer
    -0.35
    citep
    -0.34
    ajuato
    -0.34
     MainAxisSize
    -0.34
     Cub
    -0.33
    POSITIVE LOGITS
     definition
    3.31
     definitions
    2.92
     Definition
    2.83
    definition
    2.81
     define
    2.72
     defin
    2.69
    Definition
    2.66
     definición
    2.64
     definição
    2.63
    定義
    2.61
    Activations Density 1.486%

    No Known Activations