© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29454
    Prev
    Next
    INDEX
    Explanations

    terms related to academic submission and peer review processes

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

    legal and financial transactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.93
    الإنجليزية
    -0.76
    StructEnd
    -0.68
    httphttps
    -0.65
    MigrationBuilder
    -0.62
    protoimpl
    -0.61
     متعلقه
    -0.60
     AssemblyCulture
    -0.59
    IntoConstraints
    -0.53
    WriteTagHelper
    -0.52
    POSITIVE LOGITS
     themſelves
    0.60
     therefrom
    0.57
     tatsäch
    0.57
     WaitForSeconds
    0.56
     himſelf
    0.56
    จริง
    0.56
    ัติ
    0.56
    nebago
    0.56
     successfully
    0.54
    haga
    0.54
    Activations Density 0.215%

    No Known Activations