© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 5206
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical regions, particularly those associated with the term "West."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.68
    Personendaten
    -0.51
     iVar
    -0.49
     HttpNotFound
    -0.49
     المعيارى
    -0.48
    IActionResult
    -0.45
    MeasureSpec
    -0.45
    ValueStyle
    -0.45
    يميديا
    -0.44
    inquirer
    -0.43
    POSITIVE LOGITS
    West
    0.57
     West
    0.54
     Virginia
    0.53
     Oeste
    0.53
    side
    0.52
     Coast
    0.52
     coast
    0.49
     Side
    0.49
     Indies
    0.49
    fall
    0.49
    Activations Density 0.104%

    No Known Activations