© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7150
    Prev
    Next
    INDEX
    Explanations

    coding-related keywords and class definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Initialization, constructors, and UI setup

    np_acts-logits-general · gemini-2.0-flash

    initialize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RemoveAt
    -0.50
     removeFrom
    -0.50
    stringify
    -0.47
     shutil
    -0.47
    ษัท
    -0.45
    CopyWith
    -0.45
    showConfirm
    -0.45
    removeFrom
    -0.44
    ToSend
    -0.43
    EndGlobalSection
    -0.43
    POSITIVE LOGITS
     init
    1.79
    init
    1.71
     initialize
    1.70
    Init
    1.58
     Init
    1.56
     initialization
    1.50
     Initialize
    1.50
    initialize
    1.50
    初始化
    1.46
    Initialize
    1.43
    Activations Density 0.190%

    No Known Activations