© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8287
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "proper" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding words related to correctness or suitability

    np_acts-logits-general · gemini-2.0-flash

    proper execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gweler
    -0.48
    Vinc
    -0.46
    DataField
    -0.41
     portfolio
    -0.40
    uncu
    -0.40
    portfolio
    -0.39
    picasso
    -0.39
    indata
    -0.37
    Ngu
    -0.37
    Currency
    -0.37
    POSITIVE LOGITS
    Proper
    2.09
     proper
    2.03
     Proper
    2.00
    proper
    1.98
     PROPER
    1.98
     properly
    1.77
    properly
    1.69
     Properly
    1.64
     correctement
    1.22
     Improper
    1.19
    Activations Density 0.247%

    No Known Activations