© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 12359
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal expression and emotional engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    msgTypes
    -0.66
    optionalTypeArgs
    -0.56
    AnimationsModule
    -0.54
    DockStyle
    -0.50
    setVerticalGroup
    -0.49
    Atsauces
    -0.49
    يكب
    -0.49
    CppMethod
    -0.49
     виправивши
    -0.49
    writeFieldEnd
    -0.49
    POSITIVE LOGITS
     themselves
    3.73
     herself
    3.69
     himself
    3.59
     yourself
    3.56
     ourselves
    3.47
     itself
    3.45
    themselves
    3.14
     myself
    3.05
    himself
    3.03
    itself
    2.98
    Activations Density 0.728%

    No Known Activations