© 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. 35-GEMMASCOPE-RES-16K
    11. 9050
    Prev
    Next
    INDEX
    Explanations

    key details related to proposals, solutions, and their significance or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المناصب
    -0.52
    GOTREF
    -0.42
    новништво
    -0.39
    ędzynarod
    -0.38
     CreateTagHelper
    -0.37
    록
    -0.36
    ędzy
    -0.36
     nė
    -0.35
    限り
    -0.35
    Tembelea
    -0.34
    POSITIVE LOGITS
     lies
    2.70
     lie
    2.44
     lying
    2.09
     Lies
    1.87
     Lying
    1.84
     lay
    1.79
    Lying
    1.77
     Lie
    1.65
    Lies
    1.64
     lied
    1.60
    Activations Density 0.507%

    No Known Activations