© 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. 4777
    Prev
    Next
    INDEX
    Explanations

    references to towers

    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
    rungsseite
    -1.00
    verwijspagina
    -0.91
    Personendaten
    -0.90
    webElementXpaths
    -0.88
    DBNull
    -0.87
    parsedMessage
    -0.80
    __*/
    -0.77
    EndGlobalSection
    -0.76
    onViewCreated
    -0.76
     dataSnapshot
    -0.75
    POSITIVE LOGITS
     tower
    0.99
     towers
    0.90
    tower
    0.86
    Tower
    0.86
     Tower
    0.84
    eqnarray
    0.67
    towers
    0.67
     Towers
    0.66
     TOWER
    0.64
     aesthetic
    0.61
    Activations Density 0.065%

    No Known Activations