© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103426
    Prev
    Next
    INDEX
    Explanations

    terms related to data structures and values in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    foglal
    -0.43
     interesar
    -0.33
     gouvern
    -0.30
    bentar
    -0.30
     pimpinan
    -0.30
     повіт
    -0.28
     kated
    -0.28
    ガネ
    -0.28
    とおり
    -0.28
    vē
    -0.28
    POSITIVE LOGITS
     very
    0.75
     extremely
    0.72
     highly
    0.69
     relatively
    0.67
     unique
    0.65
    ValueStyle
    0.64
     different
    0.63
     distinct
    0.61
     fairly
    0.60
     pleasant
    0.59
    Activations Density 0.012%

    No Known Activations