© 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. 3-GEMMASCOPE-RES-16K
    11. 80
    Prev
    Next
    INDEX
    Explanations

    mentions of the programming language C++

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.78
     EventArgs
    -0.78
    enumii
    -0.76
     للمعارف
    -0.67
    ScopeManager
    -0.61
    cuidado
    -0.59
     gange
    -0.57
    ImageIO
    -0.53
     UnityEngine
    -0.53
    someone
    -0.51
    POSITIVE LOGITS
    cpp
    1.39
     cpp
    1.06
    (!__
    0.90
     Roskov
    0.84
    Cpp
    0.81
    stereotype
    0.81
    FormTagHelper
    0.80
     ComVisible
    0.76
    migrations
    0.74
    colgroup
    0.72
    Activations Density 0.009%

    No Known Activations