© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12290
    Prev
    Next
    INDEX
    Explanations

    instances of database-related terminology and elements, particularly involving cadmium

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    iK
    -0.42
    ZB
    -0.40
    HTTPClient
    -0.40
    APA
    -0.40
    QZ
    -0.39
    UserID
    -0.39
    classID
    -0.39
    userID
    -0.39
    ProductID
    -0.39
    YV
    -0.39
    POSITIVE LOGITS
     Cd
    1.22
     Db
    1.16
     Ct
    1.09
     Cv
    1.09
     Md
    1.09
     Tv
    1.05
     Pd
    1.04
     Cc
    1.04
     Pb
    1.02
     Cb
    1.02
    Activations Density 0.376%

    No Known Activations