© 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. 36-GEMMASCOPE-RES-16K
    11. 14141
    Prev
    Next
    INDEX
    Explanations

    programming constructs and concepts related to Kotlin code structure and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.82
    CppMethod
    -0.73
    
    -0.64
     ModelExpression
    -0.62
    GraphicsUnit
    -0.60
    principalColumn
    -0.59
     MainAxisSize
    -0.58
    +#+#
    -0.57
     CallOverrides
    -0.56
    enterOuterAlt
    -0.55
    POSITIVE LOGITS
    !!
    0.48
     drop
    0.44
     let
    0.44
     Int
    0.40
    !!.
    0.38
    drop
    0.38
     !!
    0.37
     aplicar
    0.37
     min
    0.36
     match
    0.36
    Activations Density 0.359%

    No Known Activations