© 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. 40-GEMMASCOPE-RES-16K
    11. 7193
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate uncertainty or questioning of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.51
     colorear
    -0.40
    httphttps
    -0.39
    -------------</
    -0.36
    CppCodeGen
    -0.35
    hfill
    -0.35
     wpływ
    -0.35
    findpost
    -0.35
    }}/>
    -0.35
    copyWith
    -0.34
    POSITIVE LOGITS
     works
    2.86
     worked
    2.42
     Works
    2.34
     WORKS
    2.33
    Works
    2.19
    works
    2.14
    worked
    2.08
     Worked
    2.08
    Worked
    2.00
    WORKS
    1.89
    Activations Density 1.038%

    No Known Activations