© 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. 11-GEMMASCOPE-RES-16K
    11. 10030
    Prev
    Next
    INDEX
    Explanations

    phrases that include descriptors of complexity or reasonableness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.87
     doInBackground
    -0.86
     nakalista
    -0.84
    :✨
    -0.83
     Majefty
    -0.83
    anskje
    -0.80
     ContentValues
    -0.80
     EClass
    -0.75
    ethene
    -0.75
    Przeczytaj
    -0.74
    POSITIVE LOGITS
     very
    0.55
     a
    0.55
     hard
    0.52
     difficult
    0.52
     not
    0.51
    ↵↵
    0.51
     full
    0.49
    N
    0.47
     
    0.46
     time
    0.46
    Activations Density 0.153%

    No Known Activations