© 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. 3257
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and task management within a software context

    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
     []:
    -1.06
     createSlice
    -0.84
     BoxFit
    -0.82
    iVar
    -0.82
    DebuggerNonUser
    -0.75
    AnchorStyles
    -0.72
    ✨:
    -0.71
     calendriers
    -0.71
    ConstraintMaker
    -0.70
    IntoConstraints
    -0.69
    POSITIVE LOGITS
    Tasks
    1.24
     tasks
    1.07
     Tasks
    1.02
    tasks
    0.91
     task
    0.87
    MathML
    0.80
    TASKS
    0.75
     Task
    0.69
    GEBURTS
    0.67
    task
    0.64
    Activations Density 0.007%

    No Known Activations