© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4285
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure elements related to function definitions and method calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteBarrier
    -0.89
    principalTable
    -0.78
    rungsseite
    -0.75
    PerformLayout
    -0.75
     nahilalakip
    -0.71
    GOTREF
    -0.71
    MigrationBuilder
    -0.70
    tagHelperRunner
    -0.68
     "))
    -0.68
    Hozzáférés
    -0.68
    POSITIVE LOGITS
    TagMode
    0.64
    )
    0.58
     تعدى
    0.58
     uſe
    0.54
     HasFactory
    0.53
    Населення
    0.53
     purpoſe
    0.53
     ſame
    0.52
     femininity
    0.52
     ſtate
    0.51
    Activations Density 0.322%

    No Known Activations