© 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. 12-GEMMASCOPE-RES-16K
    11. 8653
    Prev
    Next
    INDEX
    Explanations

    patterns of letters or sequences that represent specific combinations or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.78
    ViewImports
    -0.70
    Personendaten
    -0.64
    styleType
    -0.60
    OGND
    -0.60
    CppMethod
    -0.60
     ujednoznacz
    -0.59
    RectangleBorder
    -0.58
     مشين
    -0.58
    UserScript
    -0.57
    POSITIVE LOGITS
    qrstuvwxyz
    0.36
    ★★★★☆
    0.33
    Observable
    0.31
     run
    0.31
     poli
    0.30
     Three
    0.29
    Three
    0.29
    三大
    0.28
    Run
    0.28
     Open
    0.28
    Activations Density 1.104%

    No Known Activations