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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 2141
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and constructs, particularly those associated with functions and expressions

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

    Code, JSON, config file structures

    np_acts-logits-general · gemini-2.0-flash

    German words starting with "Sch"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.66
    queryInterface
    -0.61
     Infórmanos
    -0.60
    сылкі
    -0.56
     geſch
    -0.53
    期刊论文
    -0.52
     الرياضيه
    -0.52
    oredCriteria
    -0.51
    arsky
    -0.50
    usermodel
    -0.50
    POSITIVE LOGITS
     handleMessage
    0.31
    XmlAccessorType
    0.31
     Schö
    0.30
     Schlegel
    0.29
    ̈́
    0.28
    🔀
    0.28
    rungsseite
    0.27
     Schne
    0.27
     Schick
    0.27
     Schra
    0.26
    Activations Density 0.163%

    No Known Activations