© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3524
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions of experimental techniques in scientific research

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

    discussing, describing, explaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.58
     GenerationType
    -0.56
    ViewImports
    -0.56
    IUrlHelper
    -0.55
    angal
    -0.54
    lccn
    -0.53
    stateMutability
    -0.53
    MigrationBuilder
    -0.52
    டைய
    -0.51
    internalType
    -0.51
    POSITIVE LOGITS
     discuss
    1.75
     discusses
    1.74
     discussing
    1.59
     discussion
    1.52
     explain
    1.51
     describe
    1.51
     discussed
    1.50
     describes
    1.44
     Discuss
    1.36
     description
    1.36
    Activations Density 0.283%

    No Known Activations