© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 9051
    Prev
    Next
    INDEX
    Explanations

    compound words or terms related to biological or chemical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.59
     kasarigan
    -0.49
     الحره
    -0.45
    次
    -0.45
    Diweddarwch
    -0.45
    #+#
    -0.44
    ע
    -0.43
    WriteTagHelper
    -0.43
     dAtA
    -0.42
    ственными
    -0.42
    POSITIVE LOGITS
     GenerationType
    0.42
    Хьажоргаш
    0.37
    am
    0.37
     LoggerFactory
    0.35
    EndContext
    0.34
    割
    0.32
    ablemente
    0.32
    rane
    0.32
    Rhestr
    0.31
    ambu
    0.30
    Activations Density 0.259%

    No Known Activations