© 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. 2-GEMMASCOPE-RES-16K
    11. 8445
    Prev
    Next
    INDEX
    Explanations

    expressions indicating newness or beginner status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -0.53
    roch
    -0.47
     "
    -0.45
     ir
    -0.43
    供
    -0.43
     prí
    -0.43
     en
    -0.41
     zu
    -0.40
     bij
    -0.40
     ti
    -0.39
    POSITIVE LOGITS
     myſelf
    1.28
     Shakspeare
    1.06
     Efq
    0.96
     themſelves
    0.93
     Wikimédia
    0.90
     reaſon
    0.90
     himſelf
    0.89
     Monfieur
    0.87
     houſe
    0.86
    EndContext
    0.86
    Activations Density 0.407%

    No Known Activations