© 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. 38-GEMMASCOPE-RES-16K
    11. 11907
    Prev
    Next
    INDEX
    Explanations

    instances of numerical data or references within scientific or technical texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.82
    Personendaten
    -0.78
     vii
    -0.77
    OGND
    -0.74
     XXVII
    -0.74
    ⑦
    -0.73
    UserScript
    -0.73
    ੝
    -0.73
     gyhoeddwyd
    -0.72
     ProtoMessage
    -0.71
    POSITIVE LOGITS
    Spacing
    0.27
     Windsor
    0.26
    hw
    0.26
     esposo
    0.26
    KeyValuePair
    0.26
     مجلس
    0.25
    Save
    0.25
     cuerdas
    0.25
     space
    0.25
     ahor
    0.24
    Activations Density 0.678%

    No Known Activations