© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15366
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationships or conditions between entities, often expressed through relative clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dė
    -0.59
    らう
    -0.57
    醐
    -0.53
     ferie
    -0.53
     vieja
    -0.53
    fallen
    -0.52
     ratify
    -0.52
     waking
    -0.52
     Team
    -0.52
    drücken
    -0.52
    POSITIVE LOGITS
     who
    1.08
     ambao
    0.94
     which
    0.93
     []:
    0.92
     οποίο
    0.91
    which
    0.86
     które
    0.85
    who
    0.84
     quien
    0.83
     والذي
    0.82
    Activations Density 0.373%

    No Known Activations