© 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. 4001
    Prev
    Next
    INDEX
    Explanations

    terms related to programming languages and frameworks, particularly focusing on specific keywords like "Razor" and "LogFactory"

    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
    mergeFrom
    -0.80
     kasarigan
    -0.79
    OGND
    -0.66
     in
    -0.55
     Willis
    -0.55
     anillos
    -0.54
    ynomial
    -0.54
     Bioaccumulative
    -0.53
    InitVars
    -0.52
    葩
    -0.52
    POSITIVE LOGITS
    Razor
    2.53
     Razor
    2.00
     razor
    1.54
    razor
    1.39
     houſe
    1.02
     Houſe
    0.94
     Jefus
    0.94
     RAZ
    0.93
     purpoſe
    0.91
     myſelf
    0.88
    Activations Density 0.005%

    No Known Activations